Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 14740
    Prev
    Next
    INDEX
    Explanations

    content related to persecution and conflict experienced by specific groups or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.69
    TagMode
    -0.59
     Betracht
    -0.53
    holder
    -0.51
    humanité
    -0.49
    entance
    -0.48
    ườ
    -0.48
    ضور
    -0.47
    optString
    -0.47
     assembly
    -0.47
    POSITIVE LOGITS
     persecution
    0.66
     persecu
    0.64
     perse
    0.63
     persecuted
    0.59
     estekak
    0.59
     Rejection
    0.58
    jmniej
    0.58
    resistant
    0.54
     rejection
    0.53
    ้ง
    0.51
    Activations Density 0.354%

    No Known Activations