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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16187
    Prev
    Next
    INDEX
    Explanations

    terms related to shifts and transitions in various contexts

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

    "shift" or "shifted"

    np_acts-logits-general · gemini-2.0-flash

    shift and moves

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Autoritní
    -0.38
    EndInit
    -0.33
    
    -0.32
    webElementGuid
    -0.31
     OnInit
    -0.30
    ísticas
    -0.30
    richTextPanel
    -0.30
    raten
    -0.29
    isalpha
    -0.29
    wrappers
    -0.28
    POSITIVE LOGITS
     shifted
    1.91
     shift
    1.82
     shifting
    1.72
    Shift
    1.65
    shift
    1.64
    shifted
    1.64
     Shift
    1.63
     shifts
    1.57
     Shifting
    1.56
    shifting
    1.50
    Activations Density 0.731%

    No Known Activations