© 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. 5776
    Prev
    Next
    INDEX
    Explanations

    terms related to power dynamics and social hierarchy

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

    influence or control ("power", "wield")

    np_acts-logits-general · gemini-2.0-flash

    wielding influence and power

    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
    GEBURTS
    -0.49
    ticus
    -0.46
    gelopen
    -0.45
    InputTagHelper
    -0.44
     Joi
    -0.43
    adget
    -0.41
    kiri
    -0.41
    SuppressLint
    -0.41
     AutoMapper
    -0.40
    öns
    -0.40
    POSITIVE LOGITS
     power
    3.33
    power
    3.00
    Power
    2.70
     Power
    2.69
     POWER
    2.62
    POWER
    2.57
     powers
    2.32
    powers
    2.19
     powerful
    2.10
     puissance
    2.10
    Activations Density 0.449%

    No Known Activations