Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 5382
    Prev
    Next
    INDEX
    Explanations

    terms related to communication and questioning in a review or inquiry context

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

    preceding verbs or pronouns

    np_acts-logits-general · gemini-2.0-flash

    working documents

    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
     wikipagina
    -0.42
     resourceCulture
    -0.41
    BeginContext
    -0.41
    İstinadlar
    -0.39
    Халык
    -0.39
     membayar
    -0.38
     Meksiku
    -0.38
     PyTuple
    -0.37
    archiviato
    -0.36
     nového
    -0.36
    POSITIVE LOGITS
    的工作
    0.53
    OfWork
    0.52
     discretion
    0.51
     working
    0.47
     Workspace
    0.45
     diag
    0.43
     himself
    0.42
     WORK
    0.42
     WORKING
    0.42
     prec
    0.41
    Activations Density 0.930%

    No Known Activations