© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13599
    Prev
    Next
    INDEX
    Explanations

    sections and summaries in academic or formal documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to formal paper organization (sections, conclusions, summaries) and standardized statistical reporting (tests, p-values, significance thresholds).

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    transitional phrases that conclude academic or formal document sections, particularly indicating structural organization or final remarks.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TargetException
    -0.47
    diag
    -0.46
    GIVEREF
    -0.45
    новништво
    -0.44
    enga
    -0.44
    allenge
    -0.42
     Defic
    -0.42
    olume
    -0.42
    cove
    -0.42
    colgroup
    -0.42
    POSITIVE LOGITS
    WebVitals
    0.48
    Personendaten
    0.47
    DockStyle
    0.47
    ISupport
    0.46
     незавершена
    0.43
     estekak
    0.42
    disposing
    0.42
    SequentialGroup
    0.39
     חיצוניים
    0.37
    AndroidJUnit
    0.37
    Activations Density 0.169%

    No Known Activations