© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1552
    Prev
    Next
    INDEX
    Explanations

    citations and references to academic publications

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

    IEEE publications and academic volumes

    np_acts-logits-general · gemini-2.0-flash

    IEEE papers, engineering, vol, pp

    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
     queſta
    -0.49
    ☸
    -0.49
    पया
    -0.48
     indy
    -0.44
    Uber
    -0.43
     adult
    -0.43
    DotNetBar
    -0.43
    elry
    -0.43
     Prä
    -0.43
     adu
    -0.42
    POSITIVE LOGITS
     IEEE
    0.66
    IEEE
    0.59
     ingenieros
    0.45
    DataSnapshot
    0.45
     engineering
    0.41
     Engineers
    0.41
    triangleq
    0.40
    Điện
    0.40
    AnimationsModule
    0.40
    engineering
    0.40
    Activations Density 0.243%

    No Known Activations