© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 10660
    Prev
    Next
    INDEX
    Explanations

    phrases related to decision-making or opinions

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

    phrases containing the word "but" followed by action verbs or continuations showing persistence despite obstacles.

    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
    뀜
    -0.45
     للاسماء
    -0.45
     Ceinture
    -0.44
     Exactos
    -0.43
    auxite
    -0.41
     stránka
    -0.41
    олові
    -0.41
    sscanf
    -0.40
    GIVEREF
    -0.40
    뀐
    -0.40
    POSITIVE LOGITS
     anyway
    3.80
     anyways
    3.45
    anyway
    3.30
     anyhow
    2.98
     Anyway
    2.94
    Anyway
    2.92
     nonetheless
    2.88
     nevertheless
    2.80
     Anyways
    2.72
    Anyways
    2.63
    Activations Density 1.434%

    No Known Activations