© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3074
    Prev
    Next
    INDEX
    Explanations

    phrases involving the concept of "certain" specific characteristics or conditions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    the word "certain" appearing before nouns or noun phrases.

    oai_token-act-pair · claude-4-5-haiku
    Triggered 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
    Negative Logits
    Portály
    -0.47
    enterOuterAlt
    -0.39
    sco
    -0.39
     bubble
    -0.38
     Rest
    -0.38
    </i>
    -0.38
     Sk
    -0.38
    むしろ
    -0.37
     Dom
    -0.36
     Hel
    -0.36
    POSITIVE LOGITS
     فريبيس
    0.71
     مشين
    0.63
     amount
    0.62
    amount
    0.59
     doInBackground
    0.58
     صوتيه
    0.54
    特定
    0.54
     "..\..\..\
    0.53
    Certain
    0.53
    ChildScrollView
    0.52
    Activations Density 0.101%

    No Known Activations