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. 748
    Prev
    Next
    INDEX
    Explanations

    HTML and structured markup elements in the text

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

    XML/HTML tags and attributes

    np_acts-logits-general · gemini-2.0-flash

    match tags surrounding pcre

    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
     OFDb
    -1.13
     surla
    -1.05
     queſta
    -1.04
    oredCriteria
    -1.02
    ſchaft
    -1.02
     المعيارى
    -1.02
     beſch
    -0.99
     Geſch
    -0.98
     Italijani
    -0.98
    Personendaten
    -0.98
    POSITIVE LOGITS
    I
    0.38
    1
    0.37
    ↵↵
    0.35
    ↵
    0.35
    Is
    0.34
    X
    0.33
    ↵↵↵
    0.32
     I
    0.32
    From
    0.32
    。
    0.32
    Activations Density 0.086%

    No Known Activations