© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 13789
    Prev
    Next
    INDEX
    Explanations

    mathematical functions and properties related to convergence and bounding behaviors

    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
    Externí
    -0.33
     toy
    -0.29
     simplifié
    -0.28
    众
    -0.26
     Traveler
    -0.26
    NameValuePair
    -0.26
     Stodd
    -0.26
    眾
    -0.25
     camp
    -0.25
     travel
    -0.25
    POSITIVE LOGITS
    makeText
    0.70
     հղումներ
    0.70
    AnimationsModule
    0.64
     CURIAM
    0.62
    parsedMessage
    0.60
    AddTagHelper
    0.59
    Rujuakan
    0.57
    ✭
    0.56
     canlynol
    0.56
    Aholisi
    0.56
    Activations Density 1.813%

    No Known Activations