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. 17-GEMMASCOPE-RES-16K
    6. 5879
    Prev
    Next
    INDEX
    Explanations

    words related to absurdity or illogical situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Liens
    -0.65
    Biographie
    -0.65
    i
    -0.62
    ه
    -0.62
    UVWXYZ
    -0.59
    WebVitals
    -0.59
    VAO
    -0.58
    };*/
    -0.57
    </table>
    -0.57
     مشارکت‌کنندگان
    -0.57
    POSITIVE LOGITS
    ded
    0.89
    ding
    0.74
     Kud
    0.67
     unknownFields
    0.66
    dddd
    0.65
    der
    0.65
     continúas
    0.64
     BUD
    0.64
    died
    0.63
    DDDD
    0.62
    Activations Density 2.188%

    No Known Activations