Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15721
    Prev
    Next
    INDEX
    Explanations

    statements about scientific consensus and accepted truths

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

    preceding "consensus," "generally," or "widely."

    np_acts-logits-general · gemini-2.0-flash

    widely accepted consensus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    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
     poffe
    -0.48
     AssemblyTitle
    -0.48
     Chwiliwch
    -0.47
     незавершена
    -0.46
     poffible
    -0.46
     purpoſe
    -0.46
     ſte
    -0.45
    RegistryLite
    -0.44
    Predecesor
    -0.43
     Roskov
    -0.43
    POSITIVE LOGITS
     consensus
    1.73
    consensus
    1.40
     accepted
    1.38
     Consensus
    1.30
     consenso
    1.28
    Consensus
    1.22
    accepted
    1.17
     prevailing
    1.09
     widely
    1.07
     generally
    1.06
    Activations Density 0.447%

    No Known Activations