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. 6297
    Prev
    Next
    INDEX
    Explanations

    semicolons in code or text blocks

    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
    ↵↵↵
    -0.57
    ab
    -0.53
    可
    -0.51
    trans
    -0.49
     zab
    -0.48
     AB
    -0.47
     可
    -0.47
    ret
    -0.47
     ab
    -0.47
    рет
    -0.46
    POSITIVE LOGITS
    帖最后由
    1.39
     nahilalakip
    1.35
    AddTagHelper
    1.20
     CreateTagHelper
    1.18
    */;
    1.17
    AxisAlignment
    1.15
    enumi
    1.10
    RectangleBorder
    1.08
    )");
    
    1.05
    SBATCH
    1.03
    Activations Density 0.020%

    No Known Activations