© 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. 22-GEMMASCOPE-RES-16K
    11. 13690
    Prev
    Next
    INDEX
    Explanations

    programming language constructs and syntax related to defining functions and parameters

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

    before parameters/arguments

    np_acts-logits-general · gemini-2.0-flash

    specified value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.79
     Paglinawan
    -0.74
    __*/
    -0.56
    __':
    -0.55
    ↵↵
    -0.54
    __":
    -0.54
     pioggia
    -0.53
    مراجع
    -0.50
     tasche
    -0.50
    NameInMap
    -0.50
    POSITIVE LOGITS
     {@
    0.98
     specified
    0.91
     given
    0.88
     passed
    0.75
    specified
    0.74
     supplied
    0.73
    .
    0.68
    supplied
    0.68
     `
    0.68
     optionally
    0.65
    Activations Density 0.415%

    No Known Activations