© 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. 391
    Prev
    Next
    INDEX
    Explanations

    specific proper nouns and terms associated with historical events or organizations

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

    proper nouns and named entities, particularly names of people, places, 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
     öffnungszeiten
    -0.42
    ortunadamente
    -0.41
    theless
    -0.40
     setempat
    -0.39
     económicas
    -0.37
     kohta
    -0.37
     jengibre
    -0.37
     consecuencias
    -0.36
    zbęd
    -0.36
    })));
    -0.35
    POSITIVE LOGITS
    UserScript
    0.80
     GenerationType
    0.65
     MenuView
    0.61
    Portale
    0.60
    stdc
    0.59
     Rails
    0.56
     IActionResult
    0.56
    
    0.56
    WireFormatLite
    0.56
     indígen
    0.55
    Activations Density 0.514%

    No Known Activations