© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 2649
    Prev
    Next
    INDEX
    Explanations

    specific technical terms or concepts related to software and coding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -1.03
    CppMethod
    -0.96
    '},
    
    -0.94
    Obrázky
    -0.94
    Personendaten
    -0.90
    "):
    
    -0.87
     =",
    -0.86
    SOUNDBITE
    -0.85
    >");
    
    -0.85
    "))
    
    -0.85
    POSITIVE LOGITS
    .
    0.75
    3
    0.73
    1
    0.70
    2
    0.70
    7
    0.68
    4
    0.67
    e
    0.67
    0
    0.66
    6
    0.65
    9
    0.65
    Activations Density 0.243%

    No Known Activations