© 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. 37-GEMMASCOPE-RES-16K
    6. 4357
    Prev
    Next
    INDEX
    Explanations

    phrases related to intent and commitment in personal and professional contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -0.57
    səhifə
    -0.54
    GOTREF
    -0.53
    contentLoaded
    -0.50
    TagMode
    -0.48
    StoryboardSegue
    -0.48
    EndGlobal
    -0.46
    ThroughAttribute
    -0.44
     informée
    -0.43
     nakalista
    -0.41
    POSITIVE LOGITS
     getting
    0.73
     finding
    0.70
     acquiring
    0.66
     obtaining
    0.66
     erecting
    0.65
     retrieving
    0.64
     converting
    0.64
     making
    0.64
     selecting
    0.63
     putting
    0.63
    Activations Density 0.523%

    No Known Activations