© 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. 22-GEMMASCOPE-RES-16K
    11. 3176
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty or speculation about past actions or thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.67
     kasarigan
    -0.65
    IntoConstraints
    -0.64
     defaultstate
    -0.64
     ModelRenderer
    -0.64
     صوتيه
    -0.64
     Monfieur
    -0.63
    UrlResolution
    -0.63
    PostExecute
    -0.59
     Theſe
    -0.59
    POSITIVE LOGITS
     thought
    0.60
    以為
    0.47
     hoped
    0.46
     wondered
    0.45
     Thought
    0.44
     tadi
    0.42
     noticed
    0.41
     pensado
    0.41
    以为
    0.40
     pensó
    0.40
    Activations Density 0.281%

    No Known Activations