© 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. 31-GEMMASCOPE-RES-16K
    11. 4311
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and structure related to equations and proofs

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

    mathematical expressions and LaTeX notation in technical/academic documents.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.49
    complexContent
    -0.46
    endsection
    -0.44
    Controllo
    -0.43
     Autorizaciones
    -0.41
    aarrggbb
    -0.41
    ,‎
    -0.41
    ፩
    -0.40
    alakip
    -0.39
     насељу
    -0.39
    POSITIVE LOGITS
     had
    1.03
     seemed
    0.88
     hadn
    0.87
     Había
    0.84
     pouvaient
    0.84
     was
    0.84
     pouvait
    0.82
     había
    0.81
    seemed
    0.79
     were
    0.78
    Activations Density 2.067%

    No Known Activations