© 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. 16-GEMMASCOPE-RES-16K
    11. 9223
    Prev
    Next
    INDEX
    Explanations

    terms related to fixing or attachment

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

    "fix" or "stuck"

    np_acts-logits-general · gemini-2.0-flash

    fix or stuck

    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
    الحياه
    -0.64
     Baillargeon
    -0.59
     ivelany
    -0.57
     Kühl
    -0.53
    strokeWeight
    -0.51
    WSER
    -0.51
    τουργ
    -0.51
     egret
    -0.51
    raisemb
    -0.50
    niosek
    -0.50
    POSITIVE LOGITS
     Fix
    0.83
     Stuck
    0.82
     stuck
    0.82
    Fix
    0.80
    Stuck
    0.79
     fix
    0.79
     locked
    0.76
    fix
    0.73
     fixed
    0.73
     fixing
    0.69
    Activations Density 0.225%

    No Known Activations