© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 8789
    Prev
    Next
    INDEX
    Explanations

    references to user profiling and targeted advertising strategies

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

    Follows "if," "user," pronouns, or "@["

    np_acts-logits-general · gemini-2.0-flash

    if a person says

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     także
    -0.53
     também
    -0.49
     también
    -0.49
     pungkasnya
    -0.48
     tiež
    -0.47
     ankaŭ
    -0.45
     pungkas
    -0.45
     also
    -0.45
     myös
    -0.45
    DockStyle
    -0.44
    POSITIVE LOGITS
     say
    0.73
     suddenly
    0.68
    某
    0.67
    某个
    0.65
     someone
    0.64
     يتيمه
    0.61
     مث
    0.60
     somebody
    0.59
     Suppose
    0.58
    say
    0.58
    Activations Density 1.032%

    No Known Activations