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 - 32k
    5. 12-GEMMASCOPE-RES-32K
    6. 1824
    Prev
    Next
    INDEX
    Explanations

    references to programming or code items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.90
    đồng
    -0.85
    BagLayout
    -0.78
     doInBackground
    -0.75
    mybatisplus
    -0.73
     باخ
    -0.69
     ddelweddau
    -0.69
    TheReal
    -0.68
     lenker
    -0.67
     AllMovie
    -0.67
    POSITIVE LOGITS
     }^{*}$
    1.02
     *
    1.01
    *
    0.96
     $*$
    0.92
    :*
    0.92
    *)
    0.87
    [toxicity=0]
    0.84
    ">*
    0.83
    *),
    0.83
    ()*
    0.82
    Activations Density 0.000%

    No Known Activations