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. 0-GEMMASCOPE-RES-16K
    6. 8020
    Prev
    Next
    INDEX
    Explanations

    terms related to compliance and systems functioning in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     and
    -0.96
    ↵↵
    -0.80
    ↵
    -0.70
    ,
    -0.60
     or
    -0.55
     of
    -0.54
    .
    -0.53
     the
    -0.53
    -
    -0.53
     in
    -0.50
    POSITIVE LOGITS
    rungsseite
    1.46
    脚注の使い方
    1.46
     дописавши
    1.45
    
    1.39
    ⓧ
    1.36
     nakalista
    1.36
    +#+#
    1.35
     ब्रेकडाउन
    1.33
     متعلقه
    1.31
    UnsafeEnabled
    1.30
    Activations Density 9.164%

    No Known Activations