© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 2707
    Prev
    Next
    INDEX
    Explanations

    elements related to programming and compilation errors in code, particularly in a server context

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

    Code snippets with keywords BEGIN and END

    np_acts-logits-general · gemini-2.0-flash

    code declarations and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isContained
    -0.53
    writeValue
    -0.47
     Exactos
    -0.46
     Tiefe
    -0.46
    brandt
    -0.44
    uminen
    -0.44
    getMenuInflater
    -0.44
    ibb
    -0.43
    sizeCache
    -0.43
    evsky
    -0.42
    POSITIVE LOGITS
     definitions
    0.72
     define
    0.71
     definition
    0.69
     للمعارف
    0.68
     estekak
    0.64
     comments
    0.64
     BEGIN
    0.64
     declarations
    0.63
     defaultstate
    0.63
    DEFINITIONS
    0.63
    Activations Density 0.896%

    No Known Activations