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. 20-GEMMASCOPE-RES-16K
    6. 7643
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and structural elements in code or structured text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]--;
    -0.67
     تانيه
    -0.66
     Theſe
    -0.65
    ourite
    -0.61
    ESSOR
    -0.60
     الحره
    -0.58
    ^(@)
    -0.58
    orong
    -0.57
     bè
    -0.55
    TemporalType
    -0.55
    POSITIVE LOGITS
    #+#
    0.61
     AttributeSet
    0.53
     članak
    0.51
    ulink
    0.48
    ברס
    0.42
     conhece
    0.41
    ul
    0.41
    ValueStyle
    0.41
    Mutagenicity
    0.40
     Acapulco
    0.40
    Activations Density 0.127%

    No Known Activations