© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 5601
    Prev
    Next
    INDEX
    Explanations

    structured data categories and their values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.71
     pinulongan
    -0.65
    minecraftforge
    -0.64
    脚注の使い方
    -0.63
     Gegenteil
    -0.62
     BoxFit
    -0.61
    WEBPACK
    -0.61
     letz
    -0.60
    rhosis
    -0.60
    glEnd
    -0.59
    POSITIVE LOGITS
    first
    0.52
    IActionResult
    0.52
    sizeCache
    0.51
     first
    0.48
    WireFormat
    0.46
     ersten
    0.45
    primera
    0.45
    AddHtmlAttribute
    0.44
     cherchés
    0.44
    moveToFirst
    0.43
    Activations Density 0.687%

    No Known Activations