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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 1037
    Prev
    Next
    INDEX
    Explanations

    acts or behaviors associated with scientific research and evaluation

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

    followed by articles "the", "a", or "an"

    np_acts-logits-general · gemini-2.0-flash

    describing actions or processes

    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
    MigrationBuilder
    -0.47
     esternos
    -0.47
     virksom
    -0.46
    лтемелер
    -0.45
     termica
    -0.43
    LayoutConstraint
    -0.43
     funktioner
    -0.42
    出版年
    -0.42
     Normdatei
    -0.41
     صوتيه
    -0.41
    POSITIVE LOGITS
    uxxxx
    0.67
    setViewportView
    0.46
    SequentialGroup
    0.41
    Климат
    0.41
     propOrder
    0.40
    addPreferredGap
    0.40
    SourceChecksum
    0.39
    zarchiwizowane
    0.38
    <?,
    0.38
    +:+
    0.38
    Activations Density 1.187%

    No Known Activations