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. 10-GEMMASCOPE-RES-16K
    6. 13247
    Prev
    Next
    INDEX
    Explanations

    statements of necessity or conditions related to research and findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    исленность
    -0.66
    InitVars
    -0.60
     /\.
    -0.60
     Cis
    -0.57
    omer
    -0.56
     Bam
    -0.55
     Ols
    -0.55
     sex
    -0.55
     BorderRadius
    -0.53
    Composable
    -0.53
    POSITIVE LOGITS
    RenderAtEndOf
    0.69
    riwal
    0.69
     Infórmanos
    0.66
    XmlAccessType
    0.65
    Chúng
    0.64
     desconhe
    0.62
    multer
    0.60
    
    0.59
    ValueStyle
    0.59
    tagHelperRunner
    0.58
    Activations Density 0.579%

    No Known Activations