© 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. 557
    Prev
    Next
    INDEX
    Explanations

    mentions of personal identity and name references

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

    the speaker or author

    np_acts-logits-general · gemini-2.0-flash

    my self-references

    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
    ſſung
    -0.77
    featureID
    -0.77
    aarrggbb
    -0.69
     ſeveral
    -0.68
     ſol
    -0.68
     utafitiHapana
    -0.68
     ſta
    -0.68
    ðsíða
    -0.67
     ſei
    -0.67
     ſoll
    -0.65
    POSITIVE LOGITS
     my
    0.38
     meinen
    0.35
     me
    0.32
    staw
    0.30
     myself
    0.30
    我
    0.29
    我的
    0.28
    Teilen
    0.28
    #!/
    0.27
     miei
    0.26
    Activations Density 0.352%

    No Known Activations