© 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. 7819
    Prev
    Next
    INDEX
    Explanations

    terms related to authority and payment within the context of entertainment and media

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

    adverbs formed by adding "-ly" to adjectives.

    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
     ModelExpression
    -0.65
    RenderAtEndOf
    -0.54
     تانيه
    -0.51
     ProtoMessage
    -0.48
     Audiodateien
    -0.47
     tartalomajánló
    -0.47
    تقاوى
    -0.46
     Signalez
    -0.46
    EDEFAULT
    -0.46
     ujednoznacz
    -0.44
    POSITIVE LOGITS
     speaking
    2.97
    speaking
    2.41
     Speaking
    2.41
    Speaking
    2.36
     talking
    1.82
     hablando
    1.80
     speak
    1.70
     parlant
    1.68
     spoke
    1.53
     berbicara
    1.52
    Activations Density 0.210%

    No Known Activations