© 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. 8-GEMMASCOPE-RES-16K
    11. 8467
    Prev
    Next
    INDEX
    Explanations

    instances of the word "repeat" or its variations, indicating a focus on repetition and recurring actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fstream
    -0.64
    anthemum
    -0.61
    readFileSync
    -0.59
    bigoplus
    -0.59
    ärä
    -0.59
     Madsen
    -0.58
    ApiModelProperty
    -0.57
     Normdatei
    -0.57
     DriverManager
    -0.57
     Ge
    -0.56
    POSITIVE LOGITS
     Repe
    1.54
     repeats
    1.53
     Repeat
    1.49
     repetition
    1.48
     repeat
    1.45
     repeater
    1.44
     repeating
    1.44
    Repeat
    1.39
     Repetition
    1.38
    repe
    1.35
    Activations Density 0.140%

    No Known Activations