© 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. 11917
    Prev
    Next
    INDEX
    Explanations

    references to discussions and acknowledgments of support

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

    acknowledgments and expressions of gratitude to collaborators and supporters.

    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
     Administrativna
    -0.55
     mijne
    -0.54
     bambú
    -0.54
     médié
    -0.48
     vectorielle
    -0.47
     hyperplasia
    -0.46
     étoient
    -0.46
     paroisse
    -0.45
     saveiro
    -0.45
     poète
    -0.44
    POSITIVE LOGITS
     conversation
    2.63
     discussion
    2.50
     conversations
    2.39
     discussions
    2.33
    conversation
    2.09
    discussion
    2.09
     Conversation
    2.02
     dialogue
    1.96
     Discussion
    1.95
    Discussion
    1.91
    Activations Density 0.667%

    No Known Activations