© 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. 7-GEMMASCOPE-RES-16K
    11. 15358
    Prev
    Next
    INDEX
    Explanations

    references to swords and related terms in the context of documents or programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Haines
    -0.52
    Pop
    -0.50
     Pop
    -0.49
    sniper
    -0.48
     Keenan
    -0.48
     uLocal
    -0.48
    EEA
    -0.47
    Rptr
    -0.46
    pop
    -0.46
     Roth
    -0.45
    POSITIVE LOGITS
    boldsymbol
    1.19
     Joy
    0.67
     JOY
    0.65
     joy
    0.64
    Sword
    0.63
     الحره
    0.62
     Schwert
    0.62
    Joy
    0.61
    Portail
    0.58
     ComVisible
    0.58
    Activations Density 0.151%

    No Known Activations