© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 39-GEMMASCOPE-RES-16K
    11. 7
    Prev
    Next
    INDEX
    Explanations

    references to mathematical concepts and formulations in scientific texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Considered
    -0.40
    nameof
    -0.39
    figer
    -0.37
     considerados
    -0.36
     pertenecen
    -0.36
    Портали
    -0.36
    ∉
    -0.36
    المكان
    -0.36
     dianggap
    -0.35
    AxisAlignment
    -0.35
    POSITIVE LOGITS
     simply
    0.61
     given
    0.61
    NamedQueries
    0.56
    simply
    0.56
    propor
    0.55
     reads
    0.55
     proportional
    0.55
    reads
    0.52
     formally
    0.51
     propor
    0.50
    Activations Density 2.308%

    No Known Activations