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. 4305
    Prev
    Next
    INDEX
    Explanations

    structured programming or markup language syntax

    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
    */
    
    
    -0.62
     defaultdict
    -0.60
    ")}
    -0.60
    írus
    -0.58
    )");
    
    -0.57
    "},
    -0.57
    readFileSync
    -0.57
    ).]
    -0.56
    "]}
    -0.56
    ↵↵↵↵↵↵↵
    -0.56
    POSITIVE LOGITS
     X
    2.14
    X
    1.85
     x
    1.49
     Xs
    1.48
    getX
    1.45
     getX
    1.45
    setX
    1.28
     Xander
    1.24
    Xylene
    1.18
     Xanth
    1.17
    Activations Density 0.428%

    No Known Activations