© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6076
    Prev
    Next
    INDEX
    Explanations

    references to specific roadways and intersections

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

    Highway designations and route numbers (like Interstate numbers, State Road numbers, and their alphanumeric identifiers).

    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
     kasarigan
    -0.46
     NUKAT
    -0.42
    autorest
    -0.40
     thâm
    -0.40
    EndContext
    -0.40
     tenet
    -0.40
    jahteraan
    -0.39
     проник
    -0.39
    DataPropertyName
    -0.37
    onomía
    -0.37
    POSITIVE LOGITS
     bridge
    1.17
     bridges
    1.09
     Bridge
    0.91
     Bridges
    0.85
    bridge
    0.85
    bridges
    0.84
     Brücke
    0.83
     crossings
    0.81
     BRIDGE
    0.81
    Bridge
    0.79
    Activations Density 0.281%

    No Known Activations