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. 11853
    Prev
    Next
    INDEX
    Explanations

    bracketed structures or nested items in text

    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
    ])->
    -0.58
     macam
    -0.53
    }}/>
    -0.53
    }}</
    -0.50
    "]));
    -0.50
    ()")
    -0.49
    )__
    -0.48
    '])->
    -0.48
    ]='\
    -0.48
    deutscher
    -0.48
    POSITIVE LOGITS
    Datuak
    0.94
    بوابة
    0.89
    CodeAttribute
    0.88
    HtmlAttribute
    0.84
    ViewImports
    0.78
    Diwedd
    0.74
    Portale
    0.73
    AnchorStyles
    0.72
    PreExecute
    0.72
     FontWeight
    0.72
    Activations Density 0.192%

    No Known Activations