© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 401
    Prev
    Next
    INDEX
    Explanations

    descriptive terms related to objects and materials in a project context

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

    specialized technical or domain-specific terminology and proper nouns within detailed descriptions.

    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
    __(/*!
    -0.63
    balleur
    -0.60
    arangay
    -0.60
    IVEREF
    -0.59
    Aholisi
    -0.59
     >=",
    -0.58
    \{\\
    -0.58
     laſſen
    -0.57
     gustaMe
    -0.57
     autorytatywna
    -0.57
    POSITIVE LOGITS
     –
    2.31
     —
    2.19
     --
    2.03
    —
    1.98
     -
    1.97
    --
    1.67
    ——
    1.57
     ---
    1.54
    ---
    1.49
     $-$
    1.49
    Activations Density 2.920%

    No Known Activations