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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9730
    Prev
    Next
    INDEX
    Explanations

    web links and URLs

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

    URLs beginning "http" or "https"

    np_acts-logits-general · gemini-2.0-flash

    http and https URLs

    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
     ddelweddau
    -0.67
    parsedMessage
    -0.63
     Riproduzione
    -0.60
    RegressionTest
    -0.60
    躇
    -0.59
    oredCriteria
    -0.58
    amodel
    -0.57
    ."));
    -0.57
    IndentedString
    -0.56
    ∎
    -0.55
    POSITIVE LOGITS
    https
    1.45
     https
    1.32
    http
    1.22
     http
    1.14
    ttps
    0.97
    Https
    0.84
     HTTPS
    0.78
    HTTPS
    0.73
    ://
    0.66
     www
    0.65
    Activations Density 0.059%

    No Known Activations