© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15984
    Prev
    Next
    INDEX
    Explanations

    elements related to interview processes and transcription documentation

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

    references to recorded interviews and their transcription.

    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
    picasso
    -0.47
     OMITBAD
    -0.41
     للمعارف
    -0.41
     &___
    -0.39
    IntoConstraints
    -0.38
    queryInterface
    -0.36
     kiin
    -0.36
     menim
    -0.34
    PMailer
    -0.34
    DataMember
    -0.34
    POSITIVE LOGITS
     transcript
    1.92
     transcription
    1.82
     transcripts
    1.81
     transcribed
    1.68
     Transcription
    1.64
    transcript
    1.62
     Transcript
    1.60
    transcription
    1.55
    Transcript
    1.55
    Transcription
    1.49
    Activations Density 0.692%

    No Known Activations