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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8829
    Prev
    Next
    INDEX
    Explanations

    affirmative responses and related contextual phrases indicating approval or confirmation

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

    Code-like keywords and values

    np_acts-logits-general · gemini-2.0-flash

    enabled, disabled, values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     communiquez
    -0.50
     baum
    -0.43
    osoba
    -0.40
    tagez
    -0.39
     economists
    -0.39
    audiovisuel
    -0.36
    restling
    -0.34
     Walkover
    -0.34
     giuri
    -0.33
     portfolios
    -0.33
    POSITIVE LOGITS
     EconPapers
    0.61
    SharedDtor
    0.60
    WithMany
    0.56
    intios
    0.55
    AddTagHelper
    0.53
    ftagPool
    0.52
     CreateTagHelper
    0.52
     ervan
    0.51
    ⓧ
    0.50
     thereof
    0.49
    Activations Density 1.065%

    No Known Activations