© 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. 31-GEMMASCOPE-RES-16K
    11. 9685
    Prev
    Next
    INDEX
    Explanations

    connections between activities, services, and the individuals involved

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases that enumerate or describe a range of diverse items or activities using "from...to" or similar constructions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intptr
    -0.59
    enumi
    -0.57
     Савезне
    -0.52
     Италијани
    -0.51
     (?)
    -0.50
    تقاوى
    -0.48
     Certain
    -0.47
     吋
    -0.45
     outra
    -0.43
     outro
    -0.43
    POSITIVE LOGITS
     everything
    1.28
    everything
    1.02
     ranging
    0.92
    Everything
    0.91
     Everything
    0.87
     such
    0.85
     allt
    0.82
    ranging
    0.81
     various
    0.81
     diverse
    0.79
    Activations Density 0.621%

    No Known Activations