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

    Neuronpedia

    Jacobian LensNEW
    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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2003
    Prev
    Next
    INDEX
    Explanations

    expressions indicating precision or exactness in context

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

    "exact" or "precise"

    np_acts-logits-general · gemini-2.0-flash

    exact details and specifications

    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
    lenme
    -0.51
     Rivas
    -0.46
     consideramos
    -0.46
     invitamos
    -0.45
    engah
    -0.44
     extranjera
    -0.43
     Maier
    -0.43
    🏾
    -0.42
    WB
    -0.42
     Parteien
    -0.41
    POSITIVE LOGITS
     Accurate
    0.93
    precise
    0.92
    Accurate
    0.92
    Exact
    0.91
     Exact
    0.91
     exact
    0.90
    Precise
    0.90
    exact
    0.89
     EXACT
    0.89
     Precise
    0.87
    Activations Density 0.129%

    No Known Activations