© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13792
    Prev
    Next
    INDEX
    Explanations

    terms related to financial details or conditions

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

    before conditions or advice

    np_acts-logits-general · gemini-2.0-flash

    instructions and advice

    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
    AnchorStyles
    -0.68
    ReusableCell
    -0.68
    enumii
    -0.64
    OGND
    -0.61
    DockStyle
    -0.60
    httphttps
    -0.60
    Hentet
    -0.59
     AssemblyTitle
    -0.59
    EndContext
    -0.58
     surla
    -0.56
    POSITIVE LOGITS
     durumda
    0.37
     înainte
    0.35
    Aholisi
    0.34
     depends
    0.33
     keputusan
    0.33
     ilmo
    0.32
     ancianos
    0.32
     skóra
    0.31
     check
    0.30
     kılıf
    0.30
    Activations Density 0.395%

    No Known Activations