© 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. 2567
    Prev
    Next
    INDEX
    Explanations

    concepts related to privacy and individual choice

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

    words and phrases that convey personal narrative and subjective reflection.

    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
     quelquefois
    -0.70
     muß
    -0.61
     occorre
    -0.60
    bootstrapcdn
    -0.59
     skall
    -0.56
     läßt
    -0.56
     resourceCulture
    -0.55
     doskona
    -0.55
    ようだ
    -0.54
     wußte
    -0.54
    POSITIVE LOGITS
     shitty
    1.21
     fucking
    1.19
     idk
    1.16
     weirdly
    1.10
     fucked
    1.09
     fuckin
    1.09
     Idk
    1.05
     tbh
    1.03
     fuck
    1.03
     kinda
    1.01
    Activations Density 3.597%

    No Known Activations