© 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. 39-GEMMASCOPE-RES-16K
    11. 3131
    Prev
    Next
    INDEX
    Explanations

    technical programming elements related to object attributes and condition checks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oprot
    -0.60
    ftagPool
    -0.57
    +#+#
    -0.56
     BoxFit
    -0.54
     препратки
    -0.54
    pretation
    -0.54
     esternos
    -0.53
    #+#
    -0.53
    addCriterion
    -0.52
    LookAnd
    -0.52
    POSITIVE LOGITS
     ===
    1.18
     !==
    1.04
    ===
    0.96
    !==
    0.77
    ==="
    0.65
    ==='
    0.60
    StoryboardSegue
    0.34
    不同
    0.34
    ->___
    0.32
     distinto
    0.31
    Activations Density 0.257%

    No Known Activations