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. 7978
    Prev
    Next
    INDEX
    Explanations

    the presence of numerical values or quantities in a document

    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
    .
    -0.67
    。
    -0.56
     and
    -0.52
    ;
    -0.50
    ।
    -0.50
     but
    -0.48
     crossorigin
    -0.47
     tortura
    -0.44
    <eos>
    -0.44
     között
    -0.43
    POSITIVE LOGITS
     WebDriverWait
    1.14
    RenderAtEndOf
    0.89
     ***/
    0.85
    ParallelGroup
    0.83
    듦
    0.82
    });*/
    0.81
     useStyles
    0.81
    basicConfig
    0.80
     تضيفلها
    0.78
    InputBorder
    0.78
    Activations Density 0.275%

    No Known Activations