Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 53273
    Prev
    Next
    INDEX
    Explanations

    terms related to achieving or reaching goals

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

    reaching a state or level

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     endblock
    -0.68
     समीक्षाएं
    -0.64
    writeFieldEnd
    -0.61
    UserScript
    -0.61
    rungsseite
    -0.61
    Slf
    -0.61
     queſta
    -0.60
     ſich
    -0.60
     Probl
    -0.59
    IUrlHelper
    -0.59
    POSITIVE LOGITS
     attained
    0.80
     attainment
    0.74
     attain
    0.74
     attains
    0.63
     attainable
    0.61
     attaining
    0.59
    tainment
    0.58
    tainable
    0.56
    tain
    0.54
    tained
    0.50
    Activations Density 0.007%

    No Known Activations