© 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. 1-GEMMASCOPE-RES-16K
    11. 8157
    Prev
    Next
    INDEX
    Explanations

    terms related to conditional and procedural operations in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.65
    featureID
    -0.64
     queſta
    -0.59
    المكان
    -0.58
    ⟬
    -0.57
    NameInMap
    -0.56
    fromnode
    -0.56
     ActivatedRoute
    -0.54
    AnimationsModule
    -0.54
     biais
    -0.53
    POSITIVE LOGITS
    pin
    0.43
     pin
    0.37
    pon
    0.36
     pa
    0.33
    pac
    0.32
     PRAY
    0.32
     pf
    0.32
     par
    0.31
     put
    0.31
     pe
    0.30
    Activations Density 1.053%

    No Known Activations