© 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. 10065
    Prev
    Next
    INDEX
    Explanations

    phrases indicating changes to urban infrastructure or geographic features

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

    the verb "is" or "was" in contexts describing states or conditions of places and things.

    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
     Vaticano
    -0.33
    currentColor
    -0.30
    accumulative
    -0.29
     répand
    -0.27
     triomphe
    -0.26
    föl
    -0.26
     PLWABN
    -0.25
    fromCharCode
    -0.24
     транспор
    -0.24
     Exteriores
    -0.24
    POSITIVE LOGITS
     occupied
    1.07
     unoccupied
    0.94
     visited
    0.94
     reopened
    0.93
    occupied
    0.93
     flooded
    0.91
     vacated
    0.88
     Occupied
    0.88
     populated
    0.86
     deserted
    0.85
    Activations Density 0.696%

    No Known Activations