© 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
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 15991
    Prev
    Next
    INDEX
    Explanations

    information related to contact details and medical hotline resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.79
    Personensuche
    -0.62
     članak
    -0.54
     Wikimedijinoj
    -0.53
     تانيه
    -0.53
     Wiktionnaire
    -0.51
    期刊论文
    -0.51
     AssemblyTitle
    -0.50
    ngrx
    -0.49
    gonic
    -0.48
    POSITIVE LOGITS
    PyTuple
    0.41
    GTCX
    0.39
     سرا
    0.36
    :+:
    0.35
    IBAction
    0.34
    Erase
    0.34
     hotline
    0.34
    nasional
    0.33
    urlencoded
    0.32
     CanadaChoose
    0.32
    Activations Density 0.083%

    No Known Activations