© 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. 8060
    Prev
    Next
    INDEX
    Explanations

    questions and expressions of confusion or surprise

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

    question words and interrogative sentence structures, particularly "what" questions and direct inquiries.

    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
     autorytatywna
    -0.60
    OGND
    -0.59
    mybatisplus
    -0.57
     varandra
    -0.54
    ktop
    -0.54
    tagez
    -0.50
    Datuak
    -0.50
    DebuggerNonUser
    -0.49
     defaultstate
    -0.49
    stdc
    -0.49
    POSITIVE LOGITS
     exactly
    0.45
     weir
    0.44
     purpose
    0.40
     happened
    0.40
     يتيمه
    0.39
    exactly
    0.38
     strange
    0.37
     exatamente
    0.36
     weird
    0.36
     Suddenly
    0.36
    Activations Density 0.230%

    No Known Activations