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. 9096
    Prev
    Next
    INDEX
    Explanations

    code-related syntax and functions

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

    Code, XML, or JSON syntax

    np_acts-logits-general · gemini-2.0-flash

    keywords following punctuation

    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
     يتيمه
    -0.71
    SharedCtor
    -0.67
    IUrlHelper
    -0.63
    IntoConstraints
    -0.62
     surla
    -0.61
    verifyException
    -0.60
    uxxxx
    -0.59
     AttributeSet
    -0.59
     صوتيه
    -0.59
    دانشنامهٔ
    -0.58
    POSITIVE LOGITS
     tomada
    0.40
    AnchorStyles
    0.39
     Keuangan
    0.38
     combination
    0.36
     Selecciona
    0.35
     mantenido
    0.33
     Jenderal
    0.33
     Gesellschaft
    0.33
     Kerja
    0.33
     nuages
    0.33
    Activations Density 0.133%

    No Known Activations