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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 10922
    Prev
    Next
    INDEX
    Explanations

    phrases related to objections and assertions regarding fees or financial assessments

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

    like "broader", "larger", or "overall"

    np_acts-logits-general · gemini-2.0-flash

    scope or scale

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndInit
    -0.74
     nakalista
    -0.69
     <>",
    -0.68
    </thead>
    -0.67
     kaarangay
    -0.66
    NewUrlParser
    -0.66
    
    -0.65
     Exacts
    -0.59
    TintMode
    -0.59
    RTCK
    -0.57
    POSITIVE LOGITS
     overall
    2.35
     broader
    2.08
    overall
    2.07
     Overall
    1.96
    Overall
    1.92
     wider
    1.84
     general
    1.83
     larger
    1.70
     overarching
    1.64
    整體
    1.57
    Activations Density 1.014%

    No Known Activations