© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1534
    Prev
    Next
    INDEX
    Explanations

    guidance and direction in discussing plans or strategies for moving forward

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases indicating guidance and moving towards improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    moving forward

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.51
     Pelo
    -0.45
     Saratoga
    -0.45
     Eras
    -0.44
    Intr
    -0.44
     cuttings
    -0.44
    CPtr
    -0.44
     Lute
    -0.43
    KommentareTeilen
    -0.43
     Saras
    -0.43
    POSITIVE LOGITS
     forward
    1.71
    forward
    1.41
     Forward
    1.34
    Forward
    1.30
     FORWARD
    1.29
     forwards
    1.12
     вперед
    1.07
    FORWARD
    1.05
     future
    1.05
     adelante
    1.04
    Activations Density 0.095%

    No Known Activations