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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-GEMMASCOPE-RES-16K
    6. 2780
    Prev
    Next
    INDEX
    Explanations

    adjectives describing ease or difficulty in performing tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    protoimpl
    -0.67
    scriptcase
    -0.66
     onCreateView
    -0.60
     makeStyles
    -0.58
    htbp
    -0.58
     👎
    -0.58
     Biôgrafia
    -0.56
     ***!
    -0.54
     mignon
    -0.54
    klaim
    -0.53
    POSITIVE LOGITS
     colspan
    0.68
     ffilm
    0.66
    UnusedPrivate
    0.60
    übers
    0.56
    cipais
    0.55
    Susie
    0.54
     infer
    0.53
    viron
    0.52
    setof
    0.51
     leicht
    0.51
    Activations Density 0.142%

    No Known Activations