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. 25-GEMMASCOPE-RES-16K
    6. 8578
    Prev
    Next
    INDEX
    Explanations

    references to numerical data formats and symbols in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enido
    -0.48
     TextAppearance
    -0.47
     trial
    -0.47
    ReusableCell
    -0.47
     died
    -0.45
    tritts
    -0.43
    sistors
    -0.43
    てん
    -0.43
    localPosition
    -0.43
     ویکی‌پدیا
    -0.43
    POSITIVE LOGITS
    hline
    1.89
    cline
    1.24
    hdashline
    0.92
    multicolumn
    0.76
    multirow
    0.69
    帖最后由
    0.69
    GroupLayout
    0.67
     CreateTagHelper
    0.66
    toprule
    0.63
     TextInputType
    0.62
    Activations Density 0.049%

    No Known Activations