© 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-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 64336
    Prev
    Next
    INDEX
    Explanations

    the presence of the term "place" in various contexts

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

    things in place

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    MessageOf
    -0.57
     صوتيه
    -0.54
    ésult
    -0.53
     يتيمه
    -0.53
    SEGUIR
    -0.52
    Искәрмәләр
    -0.50
    oa̍t
    -0.50
    الإنجليزية
    -0.47
    centralwidget
    -0.47
    expandindo
    -0.46
    POSITIVE LOGITS
    GRANTED
    0.42
     sẵn
    0.41
    ments
    0.40
    disposing
    0.38
     мәкал
    0.38
     Keluarga
    0.36
    asList
    0.36
    ยาว
    0.36
    ghalaya
    0.36
     mechanisms
    0.35
    Activations Density 0.005%

    No Known Activations