© 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. 22-GEMMASCOPE-RES-16K
    11. 12722
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to sequential progression or steps in a process

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

    the word "step" after certain words

    np_acts-logits-general · gemini-2.0-flash

    building step

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    entrion
    -0.49
    bac
    -0.45
    textwidth
    -0.44
     समीक्षाएं
    -0.43
    اظ
    -0.42
    CheckedChanged
    -0.41
     dirilis
    -0.41
    adget
    -0.40
     recarg
    -0.39
     Whitaker
    -0.39
    POSITIVE LOGITS
     step
    4.09
    step
    3.62
     Step
    3.47
     steps
    3.39
    Step
    3.37
     STEP
    2.87
     Steps
    2.85
    steps
    2.84
    STEP
    2.79
     stepped
    2.76
    Activations Density 0.313%

    No Known Activations