© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 750
    Prev
    Next
    INDEX
    Explanations

    expressions of certainty or affirmation

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

    uncertainty or doubt

    np_acts-logits-general · gemini-2.0-flash

    absence of doubt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     doesn
    -0.57
     tidak
    -0.56
     keine
    -0.56
     nggak
    -0.55
     nobody
    -0.52
     cannot
    -0.52
     doesnt
    -0.52
     isn
    -0.51
     never
    -0.50
     aren
    -0.50
    POSITIVE LOGITS
    ChildScrollView
    0.72
    enumii
    0.52
    таратура
    0.51
     Administrativna
    0.50
     protoimpl
    0.49
    adpleegd
    0.49
    wnież
    0.49
     linkovi
    0.49
     légale
    0.48
    zbęd
    0.48
    Activations Density 0.252%

    No Known Activations