© 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. 4-GEMMASCOPE-RES-16K
    11. 9774
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "good" and related positive concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ectoria
    -0.60
     horaire
    -0.57
     springfox
    -0.51
    hline
    -0.49
     declarat
    -0.48
    append
    -0.48
    Pao
    -0.48
    gonic
    -0.48
     gait
    -0.47
     المعيارى
    -0.47
    POSITIVE LOGITS
     good
    1.60
    good
    1.54
     GOOD
    1.40
     Good
    1.34
    Good
    1.31
    GOOD
    1.31
     dobré
    1.02
     buenas
    1.00
     buena
    0.97
     goede
    0.97
    Activations Density 0.206%

    No Known Activations