© 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. 5-GEMMASCOPE-RES-16K
    11. 8773
    Prev
    Next
    INDEX
    Explanations

    the word "instead" and its variations, indicating a preference for alternatives or shifts in perspective

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "));
    -0.78
    StatusOK
    -0.74
     Cahill
    -0.73
     Hollis
    -0.73
     Kass
    -0.69
    "));
    -0.67
    Bil
    -0.67
    er
    -0.67
     Rik
    -0.66
    `{.
    -0.66
    POSITIVE LOGITS
     Instead
    1.84
    Instead
    1.82
     instead
    1.78
    instead
    1.70
     Rather
    1.23
    uttosto
    1.22
    Rather
    1.17
     rather
    1.08
    tdessen
    1.05
     Statt
    1.04
    Activations Density 0.180%

    No Known Activations