© 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. 9854
    Prev
    Next
    INDEX
    Explanations

    actions and processes related to manufacturing and experimentation

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

    words related to industrial or manufacturing processes, particularly those describing how materials are physically transformed.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    past participles and passive voice constructions describing completed actions or states.

    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
     ujednoznacz
    -0.57
    pulumi
    -0.56
    Tembelea
    -0.54
     estekak
    -0.54
    åringen
    -0.47
     мәкал
    -0.47
     ProtoMessage
    -0.45
    rungsseite
    -0.45
     decoder
    -0.44
     nucleation
    -0.40
    POSITIVE LOGITS
     using
    0.69
     thoroughly
    0.63
     twice
    0.57
     extensively
    0.54
     ulang
    0.52
     properly
    0.51
     utilizando
    0.48
     TWICE
    0.48
     menggunakan
    0.48
     according
    0.47
    Activations Density 0.670%

    No Known Activations