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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 15449
    Prev
    Next
    INDEX
    Explanations

    patterns and structures involving numerical data or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.63
    ReusableCell
    -0.52
    insegna
    -0.51
     paulista
    -0.48
    onova
    -0.46
    OutputType
    -0.45
     Catalana
    -0.42
    arino
    -0.42
     Schall
    -0.42
    Partager
    -0.42
    POSITIVE LOGITS
     Roskov
    0.92
    دانشنامهٔ
    0.78
     <<<<<<<<<<<<<<
    0.67
    +#+#
    0.65
    openzeppelin
    0.65
    省市镇
    0.62
    bootstrapcdn
    0.62
     članak
    0.61
    windowFixed
    0.61
    abestanden
    0.61
    Activations Density 0.586%

    No Known Activations