© 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. 13237
    Prev
    Next
    INDEX
    Explanations

    instances of the word "work" and its variations in various contexts

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

    the word "work."

    oai_token-act-pair · gpt-4oTriggered by @christianthto

    Follows "Work"

    np_acts-logits-general · gemini-2.0-flash

    work followed by action or description

    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
    HtmlAttribute
    -0.81
    IntoConstraints
    -0.71
     BrowserModule
    -0.65
    zzleHttp
    -0.65
    JsonInclude
    -0.64
    èces
    -0.62
     PublicKey
    -0.60
    Datuak
    -0.60
     numberWith
    -0.59
    NoSuchAlgorithm
    -0.59
    POSITIVE LOGITS
     ethic
    0.88
     done
    0.70
    spaces
    0.68
    horse
    0.68
    aday
    0.67
     wonders
    0.65
    arounds
    0.63
    done
    0.61
    manship
    0.61
    horses
    0.59
    Activations Density 0.120%

    No Known Activations