© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1595
    Prev
    Next
    INDEX
    Explanations

    structured data entries or parameters

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

    Code snippets with "to" and special characters

    np_acts-logits-general · gemini-2.0-flash

    absence or negation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Nationalité
    -0.53
    ="@+
    -0.52
    DockStyle
    -0.49
    يكب
    -0.45
    AutoScaleMode
    -0.45
     kasarigan
    -0.43
    CROSSTALK
    -0.43
     ExecuteAsync
    -0.41
    verifyException
    -0.41
    〗
    -0.40
    POSITIVE LOGITS
     tampoco
    0.65
     zoude
    0.61
     żad
    0.60
     Tampoco
    0.57
     neither
    0.54
    也沒有
    0.54
    aucune
    0.54
     heller
    0.54
     nor
    0.53
     végétal
    0.51
    Activations Density 0.373%

    No Known Activations