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. 13-GEMMASCOPE-RES-16K
    6. 140
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and syntax used in equations or programming code

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

    the presence of a beginning-of-sequence token.

    oai_token-act-pair · gpt-4oTriggered by @timna
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.78
     '\\;'
    -0.71
     kaarangay
    -0.71
     Italijani
    -0.71
    </tfoot>
    -0.70
    MigrationBuilder
    -0.68
     estimés
    -0.68
     ImportError
    -0.65
    })));
    -0.64
     Lijst
    -0.64
    POSITIVE LOGITS
    haupt
    0.49
     asal
    0.47
    leiter
    0.47
     Zwiebel
    0.47
    sique
    0.46
    ulico
    0.46
    wanzig
    0.44
     Nutz
    0.44
    发表于
    0.44
     protoimpl
    0.43
    Activations Density 0.873%

    No Known Activations