© 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. 347
    Prev
    Next
    INDEX
    Explanations

    various measurements and characteristics related to products or items, particularly in technical and descriptive contexts

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

    Follows punctuation or completes sentences

    np_acts-logits-general · gemini-2.0-flash

    positive sentiment words

    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
    chitis
    -0.40
    хьтан
    -0.39
    execSQL
    -0.38
     समीक्षाओं
    -0.37
    cibility
    -0.37
    antd
    -0.36
     trailers
    -0.35
     CreateTagHelper
    -0.35
    Чыганаклар
    -0.35
    bkz
    -0.35
    POSITIVE LOGITS
     our
    0.55
    our
    0.47
     nossas
    0.46
     :).
    0.46
    excellent
    0.46
     :-)
    0.45
     nuestras
    0.45
     nossos
    0.45
    wonderful
    0.45
    fantastic
    0.44
    Activations Density 0.128%

    No Known Activations