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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6600
    Prev
    Next
    INDEX
    Explanations

    elements related to reporting, specifically focusing on details of media presentations and structural organization

    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
    findpost
    -0.65
    rungsseite
    -0.64
    ChildScrollView
    -0.61
    ymce
    -0.56
    iastes
    -0.55
    aver
    -0.52
    mybatisplus
    -0.52
    AccessorTable
    -0.52
    ViewFeatures
    -0.52
     kaynağından
    -0.52
    POSITIVE LOGITS
    ServletException
    0.65
    LikeLike
    0.63
    σθαι
    0.59
     CGRectMake
    0.59
    GEBURTS
    0.55
    ANTAGES
    0.51
     Luxus
    0.51
    altham
    0.50
     voilà
    0.50
    
    0.50
    Activations Density 1.655%

    No Known Activations