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. 7-GEMMASCOPE-RES-16K
    6. 4512
    Prev
    Next
    INDEX
    Explanations

    references to legal terms and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    assium
    -0.79
    [^
    -0.76
    ifrance
    -0.75
    WindowConstants
    -0.74
    Σε
    -0.70
     }^{[
    -0.69
    phalt
    -0.67
    gridx
    -0.63
    ([(
    -0.63
    laway
    -0.63
    POSITIVE LOGITS
     of
    1.84
    Portail
    1.01
    ]%
    0.86
     của
    0.85
    ของ
    0.84
     فريبيس
    0.83
     των
    0.82
    fillType
    0.81
    dientemente
    0.81
     behulp
    0.77
    Activations Density 4.337%

    No Known Activations