© 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. 24-GEMMASCOPE-RES-16K
    6. 1097
    Prev
    Next
    INDEX
    Explanations

    specific details related to medical study criteria and patient demographics

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

    Preceding punctuation followed by a capitalized word

    np_acts-logits-general · gemini-2.0-flash

    end of clauses or phrases

    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
    perhaps
    -0.45
    Something
    -0.41
    EDEFAULT
    -0.41
     qualcosa
    -0.41
    something
    -0.41
     tartalomajánló
    -0.40
     îna
    -0.40
     tocó
    -0.40
    maybe
    -0.40
    Perhaps
    -0.40
    POSITIVE LOGITS
     nonUne
    0.65
    aarrggbb
    0.51
    SequentialGroup
    0.47
     الحره
    0.47
    ätigkeit
    0.47
    isSuccessful
    0.46
     harmonie
    0.46
    bibfield
    0.45
     Gab
    0.44
     Democrat
    0.44
    Activations Density 1.036%

    No Known Activations