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. 12-GEMMASCOPE-RES-16K
    6. 3217
    Prev
    Next
    INDEX
    Explanations

    specific types of numerical identifiers or codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.78
     resourceCulture
    -0.74
    AntiForgeryToken
    -0.71
    HasAnnotation
    -0.67
    Suara
    -0.65
    UnusedPrivate
    -0.65
     beginnetje
    -0.64
     '\\;'
    -0.64
    IVEREF
    -0.64
     wireType
    -0.63
    POSITIVE LOGITS
    ateness
    0.51
    éndolo
    0.51
     frères
    0.50
    }';
    0.49
    .';
    0.49
     agricole
    0.49
    volkswagen
    0.47
     themselves
    0.47
     comunit
    0.47
    */;
    0.47
    Activations Density 0.053%

    No Known Activations