© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 9098
    Prev
    Next
    INDEX
    Explanations

    terms related to the conceptualization of impact, effects, and damage in various contexts

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

    "impact" or "effect" followed by "of"

    np_acts-logits-general · gemini-2.0-flash

    impact or effect

    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
    essentiel
    -0.67
    TestTools
    -0.60
    GEBURTSDATUM
    -0.59
    Viungo
    -0.57
     <<<<<<<<<<<<<<
    -0.57
    لكتر
    -0.57
     Meksiku
    -0.56
    onaceous
    -0.56
     CommonModule
    -0.56
     themſelves
    -0.56
    POSITIVE LOGITS
    SourceChecksum
    0.74
     posed
    0.66
    fulness
    0.66
     played
    0.59
     exerted
    0.59
     that
    0.54
    rungsseite
    0.50
     avuto
    0.49
    makeConstraints
    0.49
    брь
    0.49
    Activations Density 0.275%

    No Known Activations