Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 5-GEMMASCOPE-RES-16K
    6. 1823
    Prev
    Next
    INDEX
    Explanations

    phrases related to bending or deflection of materials in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    };*/
    -0.60
    ();*/
    -0.59
    egrave
    -0.59
    });*/
    -0.55
    ---*/
    -0.55
     voork
    -0.54
    livejournal
    -0.52
    zések
    -0.52
     kanssa
    -0.52
    );*/
    -0.52
    POSITIVE LOGITS
     bending
    1.54
     bend
    1.45
     Bending
    1.41
    bend
    1.37
     bends
    1.35
     bent
    1.30
    Bend
    1.25
     Bend
    1.24
     curvature
    1.14
    bending
    1.14
    Activations Density 0.389%

    No Known Activations