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. 11831
    Prev
    Next
    INDEX
    Explanations

    patterns related to URLs and encoding

    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
     snippetHide
    -1.01
    sizeCache
    -0.91
     ModelExpression
    -0.88
     disambiguazione
    -0.86
    OGND
    -0.85
    aarrggbb
    -0.85
    󠁢
    -0.84
    IonicModule
    -0.83
    RenderAtEndOf
    -0.82
    antMatchers
    -0.82
    POSITIVE LOGITS
     भाग
    0.47
    Their
    0.47
    their
    0.46
    ışık
    0.44
    ihr
    0.44
    Attrib
    0.43
    an
    0.43
     explosión
    0.42
    i
    0.41
     deras
    0.41
    Activations Density 0.019%

    No Known Activations