© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 11626
    Prev
    Next
    INDEX
    Explanations

    statements or phrases related to conditions, qualities, or characteristics of subjects

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

    instances of the verb "is" in declarative statements that establish or describe what something fundamentally is or equals.

    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
     Fits
    -0.41
     Yet
    -0.39
     apto
    -0.39
     tapis
    -0.38
     passend
    -0.36
     Sp
    -0.36
     Suitable
    -0.36
     sop
    -0.36
     YET
    -0.36
     meno
    -0.36
    POSITIVE LOGITS
     notoriously
    0.85
     inherently
    0.69
     overrated
    0.61
     univerz
    0.60
     fickle
    0.59
     inimigo
    0.58
     compleja
    0.58
     bowiem
    0.57
     makhluk
    0.57
     zawsze
    0.57
    Activations Density 0.554%

    No Known Activations