© 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. 15861
    Prev
    Next
    INDEX
    Explanations

    phrases related to opening or expansion

    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
     beetje
    -0.50
     Tale
    -0.47
    stylers
    -0.45
    Zusammenfassung
    -0.45
     Trait
    -0.45
    waitUntil
    -0.44
     itemId
    -0.44
    SharedCtor
    -0.43
    ValueStyle
    -0.43
     resultList
    -0.43
    POSITIVE LOGITS
     open
    1.34
     Open
    1.33
    Open
    1.33
     OPEN
    1.30
    open
    1.25
    OPEN
    1.23
     Opens
    1.21
     Opened
    1.19
     opened
    1.16
     opens
    1.13
    Activations Density 0.129%

    No Known Activations