© 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. 22-GEMMASCOPE-RES-16K
    6. 6317
    Prev
    Next
    INDEX
    Explanations

    specific product features and descriptions related to durability and functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.55
     autorytatywna
    -0.55
    gnore
    -0.43
     Roskov
    -0.43
    sizeCache
    -0.43
    afficheront
    -0.41
    =$?
    -0.41
    ⓧ
    -0.41
     snippetHide
    -0.41
    хьтан
    -0.40
    POSITIVE LOGITS
     ujednoznacz
    0.47
     Italijani
    0.45
    )_/¯
    0.42
     đẳng
    0.37
     eliminates
    0.36
     cuer
    0.36
     మరి
    0.35
    superior
    0.35
    overset
    0.35
     zestaw
    0.34
    Activations Density 0.222%

    No Known Activations