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. 5352
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and their professional roles or qualifications

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

    Text after "who" or "is"

    np_acts-logits-general · gemini-2.0-flash

    who clauses describing people

    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
     nødven
    -0.33
     would
    -0.33
     absolutamente
    -0.31
    Surprisingly
    -0.31
     anything
    -0.31
     estaría
    -0.31
     unexpected
    -0.31
     They
    -0.31
     everything
    -0.30
     components
    -0.30
    POSITIVE LOGITS
    AndEndTag
    0.78
    CppMethod
    0.64
    Jereo
    0.62
    posedge
    0.61
     Normdatei
    0.61
    tagHelperRunner
    0.60
    OGND
    0.59
    ViewImports
    0.59
    AddTagHelper
    0.57
     ſelbſt
    0.56
    Activations Density 0.287%

    No Known Activations