© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 455
    Prev
    Next
    INDEX
    Explanations

    references to setting and achieving goals

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

    "goal" or "goals"

    np_acts-logits-general · gemini-2.0-flash

    goals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /*
    -0.49
    ડી
    -0.48
    seamnă
    -0.48
     French
    -0.47
     Spanish
    -0.47
     Herrera
    -0.46
     Ebers
    -0.44
     Rubin
    -0.44
    writeObject
    -0.43
     VIDEOTAPE
    -0.42
    POSITIVE LOGITS
    goal
    1.30
    Goal
    1.29
     goal
    1.26
     Goal
    1.23
     GOAL
    1.16
     goals
    1.16
     Goals
    1.15
    Goals
    1.10
    goals
    1.09
    GOAL
    1.08
    Activations Density 0.122%

    No Known Activations