© 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. 5075
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence or reference to a specific object or method

    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
    GEBURTSDATUM
    -0.70
    Personendaten
    -0.66
     незавершена
    -0.64
     Administrativna
    -0.60
    MigrationBuilder
    -0.58
     trasferimento
    -0.54
    parsedMessage
    -0.53
     esternos
    -0.52
    TypedDataSet
    -0.52
     perde
    -0.51
    POSITIVE LOGITS
     specifically
    0.46
     also
    0.46
     anonymously
    0.44
     proactively
    0.44
     strategically
    0.42
     simply
    0.42
     punctu
    0.42
     euth
    0.42
     legitimately
    0.42
     ironically
    0.41
    Activations Density 0.538%

    No Known Activations