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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 638
    Prev
    Next
    INDEX
    Explanations

    references to the name "Mah" and its variations

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

    proper nouns and names, particularly surnames and multi-part names.

    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
    </thead>
    -0.55
    ulipas
    -0.47
     <=",
    -0.46
    SequentialGroup
    -0.45
    ynos
    -0.45
     reaſon
    -0.45
     cherchés
    -0.44
    RenderAtEndOf
    -0.44
    infix
    -0.44
    Fruits
    -0.43
    POSITIVE LOGITS
    LLocation
    0.50
    DialogInterface
    0.44
    BASEPATH
    0.43
     distanciation
    0.41
     Hah
    0.40
     kuh
    0.40
    koh
    0.39
     Lah
    0.39
     Mah
    0.38
    scriptcase
    0.38
    Activations Density 0.130%

    No Known Activations