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. 902
    Prev
    Next
    INDEX
    Explanations

    structured elements and references in technical documents

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

    Followed by certain punctuation or a connecting verb

    np_acts-logits-general · gemini-2.0-flash

    UI lifecycle methods

    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
     value
    -0.28
    präsident
    -0.27
     fehér
    -0.27
     
    -0.27
     Due
    -0.27
     so
    -0.26
    )^(
    -0.26
     Debido
    -0.26
    rahmen
    -0.26
    CS
    -0.26
    POSITIVE LOGITS
    EndInit
    1.57
    ISupport
    1.41
    BeginInit
    1.20
     autorytatywna
    1.19
    PerformLayout
    1.00
    ResumeLayout
    0.89
    fjspx
    0.84
     للمعارف
    0.82
    adaptiveStyles
    0.82
    OGND
    0.80
    Activations Density 0.044%

    No Known Activations