© 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. 35-GEMMASCOPE-RES-16K
    11. 5523
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal inquiries and introductions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mar
    -0.35
    t
    -0.32
     Ban
    -0.31
    र्ष
    -0.29
     Rea
    -0.28
    tests
    -0.27
    ent
    -0.27
    zi
    -0.27
     believed
    -0.27
     success
    -0.26
    POSITIVE LOGITS
     looking
    1.20
    Looking
    0.88
    looking
    0.87
     LOOKING
    0.85
     wondering
    0.84
     seeking
    0.84
     planning
    0.84
     interested
    0.83
     Looking
    0.83
     interesado
    0.82
    Activations Density 0.203%

    No Known Activations