© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 11031
    Prev
    Next
    INDEX
    Explanations

    the presence of structural elements in writing, such as organization and clarity in the presentation of information

    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
    </tr>
    -0.55
     }));
    -0.52
    ValueStyle
    -0.51
    __()
    -0.49
    )");
    -0.48
     الحره
    -0.47
     AssemblyCulture
    -0.46
    ald
    -0.46
    ')";
    -0.46
     poi
    -0.45
    POSITIVE LOGITS
     étoit
    0.75
    DockStyle
    0.71
     parteci
    0.70
     feroit
    0.68
    ImageContext
    0.67
     للمعارف
    0.67
    +#+#
    0.67
     pouvoit
    0.65
    WithFormat
    0.63
    AddHtmlAttribute
    0.63
    Activations Density 0.174%

    No Known Activations