Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 16352
    Prev
    Next
    INDEX
    Explanations

    terms related to relationships, particularly connections between people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sympathetic
    -0.42
     comparative
    -0.40
     sympathize
    -0.40
    shutil
    -0.39
     sympathi
    -0.38
     correlated
    -0.38
    synchronized
    -0.37
     JADX
    -0.35
     coincident
    -0.35
     belonging
    -0.34
    POSITIVE LOGITS
    ArrowToggle
    0.62
    Established
    0.60
     established
    0.60
    bootstrapcdn
    0.60
    DeleteBehavior
    0.60
    forged
    0.59
     forged
    0.59
    */].
    0.58
     Established
    0.57
    established
    0.57
    Activations Density 0.374%

    No Known Activations