© 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. 13668
    Prev
    Next
    INDEX
    Explanations

    specific individuals and their involvement in legal or political contexts

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

    proper nouns and named entities, particularly people's names and organizations.

    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
     reassure
    -0.43
     reassuring
    -0.41
     reassurance
    -0.39
     encouragement
    -0.34
     コメント
    -0.32
     encourag
    -0.32
     reassured
    -0.31
     encourage
    -0.31
     advice
    -0.30
     answer
    -0.30
    POSITIVE LOGITS
     accusing
    1.42
     accuses
    1.38
     accuse
    1.34
     alleging
    1.34
     accusations
    1.34
     alleges
    1.33
     accusation
    1.30
     allegations
    1.26
     allegation
    1.21
     allege
    1.21
    Activations Density 0.784%

    No Known Activations