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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1057
    Prev
    Next
    INDEX
    Explanations

    elements related to technology and product releases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    indications of product release and location details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Lets make a difference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Réponses
    -0.69
    yarnpkg
    -0.64
    SBATCH
    -0.63
    Datuak
    -0.61
    DICTION
    -0.57
    >--}}
    -0.55
    ChildScrollView
    -0.55
     intptr
    -0.54
    Tikang
    -0.54
    Enllaces
    -0.53
    POSITIVE LOGITS
    مزید
    0.55
     consultato
    0.53
    Stream
    0.50
    Bring
    0.50
     ready
    0.49
    bca
    0.49
    AutoresizingMask
    0.48
     bring
    0.47
     Bring
    0.47
     #
    0.47
    Activations Density 0.036%

    No Known Activations