© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 633
    Prev
    Next
    INDEX
    Explanations

    attributes and characteristics related to skills in a gaming or programming context

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

    programming-related keywords and structures associated with status and effects in a coding context

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

    skill and player skills

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thâu
    -0.58
     ProtoMessage
    -0.56
    Tikang
    -0.51
    strup
    -0.50
     Cronin
    -0.49
    REFER
    -0.48
    principalTable
    -0.48
     gepubliceerd
    -0.48
    oose
    -0.47
     Lin
    -0.47
    POSITIVE LOGITS
     skill
    2.66
     Skill
    2.49
    Skill
    2.44
     skills
    2.44
    skill
    2.42
     Skills
    2.33
    Skills
    2.19
    skills
    2.15
    SKILL
    2.14
     SKILLS
    2.06
    Activations Density 0.030%

    No Known Activations