© 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. 199
    Prev
    Next
    INDEX
    Explanations

    elements related to healthcare accessibility and usability improvements for individuals with disabilities

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

    technical or industrial terminology related to processes, manufacturing, and technical specifications.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    phrases describing practical applications and technical specifications in instructional or patent documents.

    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
    INCREF
    -0.50
    skjaer
    -0.39
     يتيمه
    -0.38
    なんと
    -0.37
    noinspection
    -0.36
    倒是
    -0.36
    俨
    -0.35
    tectable
    -0.35
    ajevo
    -0.34
    ただの
    -0.34
    POSITIVE LOGITS
     large
    1.05
     busy
    1.02
     complicated
    0.96
     difficult
    0.95
     heavy
    0.93
     densely
    0.90
     dense
    0.90
     sensitive
    0.89
     complex
    0.89
     delicate
    0.87
    Activations Density 1.044%

    No Known Activations