© 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. 20-GEMMASCOPE-RES-16K
    6. 9210
    Prev
    Next
    INDEX
    Explanations

    phrases describing uncertainty and complexity in situations

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

    phrases of hedging, self-correction, and meta-discourse that qualify statements or guide the reader’s understanding.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    hedging or qualifying language that expresses uncertainty, limitation, or attempts to soften statements.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UrlResolution
    -0.64
     '\\;'
    -0.55
    gridy
    -0.47
    ReusableCell
    -0.47
     outside
    -0.44
     external
    -0.44
     Inscrivez
    -0.43
     medical
    -0.42
    ChildScrollView
    -0.42
    External
    -0.42
    POSITIVE LOGITS
     nakalista
    0.69
     <<<<<<<<<<<<<<
    0.53
     estekak
    0.52
    EndContext
    0.49
    ="@+
    0.48
     ***!
    0.47
    GOTREF
    0.45
    BeginContext
    0.45
    mobileqq
    0.44
    :+:
    0.42
    Activations Density 0.436%

    No Known Activations