Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 9557
    Prev
    Next
    INDEX
    Explanations

    temperature-related data and numerical statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    –
    -0.60
    -
    -0.59
     تا
    -0.55
     to
    -0.50
    /
    -0.49
    zus
    -0.47
     
    -0.46
     až
    -0.46
    ~
    -0.45
    it
    -0.41
    POSITIVE LOGITS
     inclusive
    1.25
    inclusive
    1.20
    parsedMessage
    1.10
    NUMX
    1.09
    sizeCache
    1.08
    StoryboardSegue
    1.03
     passim
    1.03
    Vidite
    1.02
    enderror
    1.02
    WithIOException
    1.01
    Activations Density 0.598%

    No Known Activations