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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 16-GEMMASCOPE-RES-16K
    6. 21
    Prev
    Next
    INDEX
    Explanations

    the beginning of a document or section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows a capitalized word

    np_acts-logits-general · gemini-2.0-flash

    variable or code import

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yip
    -0.45
    law
    -0.44
     Mar
    -0.43
    yq
    -0.43
    MessageInfo
    -0.42
    Mar
    -0.41
    لط
    -0.40
    ällor
    -0.39
    ATTRIBUTE
    -0.39
    pouring
    -0.39
    POSITIVE LOGITS
    StoryboardSegue
    0.89
     chofe
    0.74
     elif
    0.72
    enumii
    0.69
     désolés
    0.68
     muſt
    0.66
    elif
    0.65
    cluye
    0.64
    +#+#
    0.64
    ftagPool
    0.63
    Activations Density 0.084%

    No Known Activations