© 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. 2-GEMMASCOPE-RES-16K
    6. 6884
    Prev
    Next
    INDEX
    Explanations

    strong affirmative expressions of certainty or necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.66
     UIKit
    -0.63
     Guen
    -0.60
     erv
    -0.57
    FormTagHelper
    -0.57
     nove
    -0.57
    many
    -0.56
    withId
    -0.55
     Purse
    -0.55
    Vea
    -0.55
    POSITIVE LOGITS
     absolutely
    3.00
     Absolutely
    2.83
    absolutely
    2.79
    Absolutely
    2.59
     ABSOL
    2.43
     absolut
    2.15
     absolute
    2.04
    ABSOL
    2.03
     absolutamente
    2.03
     absolument
    1.93
    Activations Density 0.047%

    No Known Activations