© 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-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 13002
    Prev
    Next
    INDEX
    Explanations

    conditional statements and mathematical comparisons in a technical or financial context

    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
     المعيارى
    -0.81
     للاسماء
    -0.70
     CreateTagHelper
    -0.69
     صوتيه
    -0.67
    Personendaten
    -0.59
     tkinter
    -0.58
    Izvori
    -0.58
    TintMode
    -0.57
     ComVisible
    -0.57
    MessageOf
    -0.56
    POSITIVE LOGITS
     minimum
    0.56
     cap
    0.53
     limit
    0.49
    országban
    0.48
     tối
    0.47
    ETRY
    0.47
     XCTest
    0.47
    menes
    0.47
     maximum
    0.47
    minimum
    0.46
    Activations Density 0.196%

    No Known Activations