© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13906
    Prev
    Next
    INDEX
    Explanations

    references to specific entities or formal names in a context

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

    HTML or code-like syntax

    np_acts-logits-general · gemini-2.0-flash

    configuration files

    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
    ModelSerializer
    -0.57
    +:+
    -0.56
    GEBURTSDATUM
    -0.55
    原始内容存档于
    -0.54
    complexContent
    -0.54
    AutoField
    -0.49
    SizeF
    -0.49
    SequentialGroup
    -0.49
    ellido
    -0.46
     Biôgrafia
    -0.46
    POSITIVE LOGITS
    eniendo
    0.42
     препратки
    0.40
    Tazama
    0.38
    ficulties
    0.38
    }{*}{
    0.38
    $_['
    0.38
     APPARATUS
    0.37
     Apparatus
    0.36
    outine
    0.36
    amentals
    0.36
    Activations Density 0.590%

    No Known Activations