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. 17-GEMMASCOPE-RES-16K
    6. 10826
    Prev
    Next
    INDEX
    Explanations

    mathematical operations or symbols commonly used in equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    him
    -0.45
    geord
    -0.45
     دا
    -0.44
    gene
    -0.42
    ja
    -0.41
     le
    -0.41
     Jedes
    -0.41
     him
    -0.41
    le
    -0.40
    it
    -0.40
    POSITIVE LOGITS
    principalColumn
    0.99
     فريبيس
    0.92
    adaptiveStyles
    0.88
    DeleteBehavior
    0.87
    exitRule
    0.83
    ]),
    
    0.83
    tvguidetime
    0.82
    AndEndTag
    0.81
     للاسماء
    0.80
    InjectAttribute
    0.79
    Activations Density 2.008%

    No Known Activations