© 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. 22-GEMMASCOPE-RES-16K
    11. 14553
    Prev
    Next
    INDEX
    Explanations

    programming language syntax elements related to control flow and case handling

    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
    postsleuth
    -0.46
     CRACK
    -0.36
     vlieg
    -0.36
    kijken
    -0.35
     geweest
    -0.34
     fopen
    -0.34
    hésite
    -0.33
     genomen
    -0.32
    Crack
    -0.32
    avaient
    -0.32
    POSITIVE LOGITS
     NSCoder
    0.54
     defStyle
    0.53
     other
    0.49
    legel
    0.49
    NewGuid
    0.47
     BoxFit
    0.47
    ViewFeatures
    0.46
     Administrativna
    0.46
    NamedQuery
    0.44
     tartalomajánló
    0.44
    Activations Density 0.138%

    No Known Activations