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. 13376
    Prev
    Next
    INDEX
    Explanations

    terms related to legendary themes and complex social interactions

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

    that begin with certain letters

    np_acts-logits-general · gemini-2.0-flash

    `or` alternatives in multiple languages

    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
     and
    -0.45
    所有的
    -0.36
     many
    -0.36
     all
    -0.35
     each
    -0.34
     every
    -0.33
     
    -0.33
     numerous
    -0.32
     tutte
    -0.31
     minden
    -0.31
    POSITIVE LOGITS
     or
    0.96
     или
    0.94
     또는
    0.88
    或
    0.86
     hoặc
    0.85
    หรือ
    0.85
     atau
    0.84
     alebo
    0.84
    或者
    0.82
    거나
    0.82
    Activations Density 0.633%

    No Known Activations