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. 5-GEMMASCOPE-RES-16K
    6. 4762
    Prev
    Next
    INDEX
    Explanations

    mathematical operators and symbols used in formulas and equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ۜ
    -0.64
    ArgsConstructor
    -0.60
    zeera
    -0.59
    APORE
    -0.57
    MZ
    -0.55
     Calvo
    -0.55
    หวัด
    -0.54
    xically
    -0.53
     Mosca
    -0.52
     الحره
    -0.51
    POSITIVE LOGITS
    NamedQueries
    0.76
    findpost
    0.74
    NOPQRST
    0.63
    textbackslash
    0.63
    epro
    0.62
     InputDecoration
    0.58
    kig
    0.58
    LookAnd
    0.58
    WhereInput
    0.58
     Skid
    0.57
    Activations Density 0.181%

    No Known Activations