© 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. 1-GEMMASCOPE-RES-16K
    11. 6834
    Prev
    Next
    INDEX
    Explanations

    instances of the word "benefit" and its variations, indicating a focus on positive outcomes and advantages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TabStop
    -0.62
    SerializedName
    -0.60
    Datuak
    -0.59
     electrophoresis
    -0.58
     Bous
    -0.55
    PickerController
    -0.54
     StyleSheet
    -0.53
    leski
    -0.52
     Nacionales
    -0.52
     roughness
    -0.52
    POSITIVE LOGITS
     benefit
    2.40
     Benefit
    1.97
    benefit
    1.95
    Benefit
    1.86
     BENE
    1.56
     benefiting
    1.42
     benefited
    1.32
     benefitted
    1.24
     profit
    1.12
     beneficio
    1.08
    Activations Density 0.086%

    No Known Activations