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. 8-GEMMASCOPE-RES-16K
    6. 4992
    Prev
    Next
    INDEX
    Explanations

    quantitative relationships and parameters in scientific data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ništ
    -0.62
     ostavi
    -0.61
    })));
    -0.58
    setSearch
    -0.55
    Sucesor
    -0.54
    ostar
    -0.54
    "]));
    -0.54
    '))
    
    -0.53
    ."));
    -0.53
     newList
    -0.53
    POSITIVE LOGITS
    setCellValue
    0.67
    IntoConstraints
    0.66
     value
    0.65
    值
    0.65
    ioutil
    0.63
    itespace
    0.62
     price
    0.61
     height
    0.61
     level
    0.60
    templateUrl
    0.60
    Activations Density 1.718%

    No Known Activations