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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6409
    Prev
    Next
    INDEX
    Explanations

    programming-related terminology, particularly in Dart and regex contexts

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

    Specific programming languages (Dart) and storage variables

    np_acts-logits-general · gemini-2.0-flash

    Dart language code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.76
     myſelf
    -0.71
     ſtre
    -0.70
     houſe
    -0.68
     faſt
    -0.68
     ſta
    -0.67
     ſte
    -0.67
     ſtate
    -0.66
     preſent
    -0.65
     ſche
    -0.64
    POSITIVE LOGITS
    dart
    0.41
    forName
    0.37
    planung
    0.36
     심
    0.36
     للاسماء
    0.35
    IVER
    0.35
     تانيه
    0.35
     sim
    0.34
     pri
    0.34
     sch
    0.33
    Activations Density 0.084%

    No Known Activations