© 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. 3293
    Prev
    Next
    INDEX
    Explanations

    numerical or statistical values related to health research

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

    numerical sequences and mathematical expressions in structured formats.

    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
    msgTypes
    -0.42
    tvguidetime
    -0.40
    TabIndex
    -0.38
     noDo
    -0.37
     cic
    -0.36
     InputDecoration
    -0.34
    تقاوى
    -0.34
    cire
    -0.34
    hilangan
    -0.32
    bibfield
    -0.32
    POSITIVE LOGITS
    AndroidJUnit
    0.54
    Espèce
    0.53
    astify
    0.51
    SerializedName
    0.51
    CompleteListener
    0.47
    PostExecute
    0.47
    RenderAtEndOf
    0.47
    发表于
    0.47
    insee
    0.46
    FailureListener
    0.46
    Activations Density 0.391%

    No Known Activations