Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8-GEMMASCOPE-RES-16K
    6. 4753
    Prev
    Next
    INDEX
    Explanations

    HTML/XML tag-like structures or attributes in a technical document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الصف
    -0.56
    folds
    -0.55
     Shum
    -0.54
    urd
    -0.54
     shoe
    -0.53
    osos
    -0.53
    uy
    -0.53
    ở
    -0.52
     Suri
    -0.52
    ϕ
    -0.52
    POSITIVE LOGITS
    "/>
    2.77
    "/>
    
    1.99
    '/>
    1.85
    }}/>
    1.77
    }/>
    1.71
    =""/>
    1.57
    "/></
    1.50
    />
    1.43
    />";
    1.35
    ")]
    1.18
    Activations Density 0.014%

    No Known Activations