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. 4-GEMMASCOPE-RES-16K
    6. 15929
    Prev
    Next
    INDEX
    Explanations

    HTML/XML tag syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mans
    -0.64
     funt
    -0.63
    пла
    -0.57
     test
    -0.55
     collo
    -0.55
    rison
    -0.55
     JUN
    -0.54
    SUND
    -0.53
    ation
    -0.52
     fri
    -0.52
    POSITIVE LOGITS
    }>
    1.45
    >\
    1.39
    >
    
    1.36
    ]>
    1.26
    )>
    1.21
    \">
    1.21
    >"
    1.20
    }}>
    1.19
     $>$
    1.18
    >$
    1.17
    Activations Density 0.367%

    No Known Activations