© 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. 3-GEMMASCOPE-RES-16K
    11. 8805
    Prev
    Next
    INDEX
    Explanations

    references to the name "Jones" and associated elements in a legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ostavi
    -0.59
     protoimpl
    -0.45
    }`).
    -0.44
     bezpiecze
    -0.44
    windowFixed
    -0.44
    >{@
    -0.43
    ")));
    -0.43
     précisé
    -0.43
     hào
    -0.42
    })`
    -0.41
    POSITIVE LOGITS
     lamp
    0.84
     bloom
    0.77
     Lamp
    0.73
     lamps
    0.72
    lamp
    0.72
    Bulb
    0.71
     Bulb
    0.68
     bulb
    0.65
     Lamps
    0.65
    Lamp
    0.65
    Activations Density 0.268%

    No Known Activations