© 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. 12-GEMMASCOPE-RES-16K
    6. 16037
    Prev
    Next
    INDEX
    Explanations

    details related to product specifications and descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     صوتيه
    -0.91
     betweenstory
    -0.87
     EconPapers
    -0.83
    ValueGeneration
    -0.82
    LEncoder
    -0.77
     дописавши
    -0.77
    IntoConstraints
    -0.73
    DockStyle
    -0.72
    OrNil
    -0.71
    styleType
    -0.71
    POSITIVE LOGITS
     
    0.56
     /
    0.50
     This
    0.50
    has
    0.49
    ashi
    0.47
    /
    0.47
    gan
    0.46
     ==
    0.46
    Recent
    0.45
     -
    0.45
    Activations Density 0.069%

    No Known Activations