© 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. 7976
    Prev
    Next
    INDEX
    Explanations

    statements and discussions related to the concept of truth

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

    the phrase "the truth is" or similar constructions introducing factual statements or honest revelations.

    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
    Informal
    -0.38
     Vereinigung
    -0.37
     McIn
    -0.36
     Herren
    -0.35
    jména
    -0.35
     כלל
    -0.34
     kort
    -0.34
    akim
    -0.33
     Domínguez
    -0.33
     Rasmussen
    -0.33
    POSITIVE LOGITS
    fulness
    0.69
    ----</
    0.69
    Truth
    0.69
     Truth
    0.66
    facts
    0.65
     truth
    0.65
     يتيمه
    0.61
     facts
    0.60
     TRUTH
    0.59
     الرياضيه
    0.58
    Activations Density 0.136%

    No Known Activations