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. 20-GEMMASCOPE-RES-16K
    6. 758
    Prev
    Next
    INDEX
    Explanations

    references to specific programming libraries or frameworks and their related components

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

    Code snippets or programming terms

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by 's'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Umum
    -0.44
     abstrato
    -0.42
    AlterField
    -0.40
    derung
    -0.38
     geométrico
    -0.37
    complexContent
    -0.36
    ConstraintMaker
    -0.35
    Insee
    -0.35
     beroep
    -0.35
    原始内容存档于
    -0.34
    POSITIVE LOGITS
     AssemblyCulture
    0.58
     IFTT
    0.58
    gdx
    0.56
     Taktlose
    0.55
    RTEE
    0.54
     nahilalakip
    0.54
     rainforest
    0.53
    :+:
    0.53
    ACHUSET
    0.52
    رشف
    0.49
    Activations Density 0.435%

    No Known Activations