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. 16-GEMMASCOPE-RES-16K
    6. 6621
    Prev
    Next
    INDEX
    Explanations

    terms related to specific biochemical substances and biological entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    ending with "ud", "ed", or "id"

    np_acts-logits-general · gemini-2.0-flash

    ending with d or ed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.78
    RetentionPolicy
    -0.71
    Życiorys
    -0.70
    /*
    -0.70
    </table>
    -0.69
    ViewFeatures
    -0.68
    hbase
    -0.68
    eater
    -0.67
    VAO
    -0.67
    };*/
    -0.66
    POSITIVE LOGITS
    ded
    1.05
     Ede
    0.82
    died
    0.81
    di
    0.79
    ding
    0.78
     BUD
    0.77
    der
    0.77
    DED
    0.76
     PED
    0.76
     Kud
    0.76
    Activations Density 1.164%

    No Known Activations