© 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. 20-GEMMASCOPE-RES-16K
    11. 133
    Prev
    Next
    INDEX
    Explanations

    technical components related to cloud computing services and applications

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

    WSO2 Carbon-related code or links

    np_acts-logits-general · gemini-2.0-flash

    cloud enterprise deployment documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     onOptions
    -0.85
     onPostExecute
    -0.79
    ########.
    -0.76
    IntoConstraints
    -0.76
     GenerationType
    -0.68
     onAnimation
    -0.68
     NSCoder
    -0.66
     pygame
    -0.65
    Vidite
    -0.65
     BoxDecoration
    -0.65
    POSITIVE LOGITS
     cloud
    0.67
     Cloud
    0.64
    cloud
    0.55
     enterprise
    0.55
     deployment
    0.52
     deployed
    0.52
    AutoScale
    0.52
     Mule
    0.51
     Enterprise
    0.51
    Cloud
    0.51
    Activations Density 0.934%

    No Known Activations