© 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. 3181
    Prev
    Next
    INDEX
    Explanations

    phrases related to special abilities or skills in a character

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

    Energy blasts and attacks

    np_acts-logits-general · gemini-2.0-flash

    energy blasts

    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
    Sucesor
    -0.67
     doInBackground
    -0.66
    triangleq
    -0.63
    RepeatedField
    -0.63
    limus
    -0.58
    PagerAdapter
    -0.55
    Diweddarwch
    -0.55
    MockBean
    -0.53
    PerformLayout
    -0.52
    Curios
    -0.52
    POSITIVE LOGITS
     blasts
    0.79
     blast
    0.78
     flames
    0.77
     energy
    0.73
     thunder
    0.70
     lightning
    0.69
     beams
    0.68
     attacks
    0.68
     flame
    0.68
     lasers
    0.68
    Activations Density 0.452%

    No Known Activations