© 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. 14385
    Prev
    Next
    INDEX
    Explanations

    phrases related to photography techniques and spatial relationships

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

    expressions indicating proximity or distance between objects or people.

    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
    httphttps
    -0.41
    istoitu
    -0.40
    uckoo
    -0.38
     arşivlendi
    -0.38
    transQ
    -0.38
    ParallelGroup
    -0.37
     złoty
    -0.33
    rungsseite
    -0.33
     matel
    -0.32
    ecycle
    -0.32
    POSITIVE LOGITS
     closer
    2.56
     close
    2.42
     nearer
    2.39
     closest
    2.39
     proximity
    2.22
     nearest
    2.20
     closeness
    2.20
    closer
    2.14
     Closer
    2.14
    Closer
    2.09
    Activations Density 0.649%

    No Known Activations