© 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. 412
    Prev
    Next
    INDEX
    Explanations

    instances of the word "transform" and its variations across various contexts

    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
     setempat
    -0.71
     Drapeau
    -0.69
     @"/
    -0.69
     Scy
    -0.68
     flamme
    -0.66
     ammat
    -0.66
    য়ে
    -0.66
    HostException
    -0.66
     sjø
    -0.65
     prochaines
    -0.65
    POSITIVE LOGITS
    transform
    2.34
     transform
    2.11
    Transform
    2.08
     Transform
    2.02
     transforms
    1.58
    TRANSFORM
    1.55
     TRANSFORM
    1.45
     transforming
    1.35
    transforms
    1.34
     transformative
    1.20
    Activations Density 0.050%

    No Known Activations