© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 597
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals and their current status or actions

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

    the occurrence of the word "currently" and its context changes regarding time

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

    past tense or continuation

    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
     becoming
    -1.18
    becoming
    -1.04
     Becoming
    -0.90
     becomes
    -0.88
    Becoming
    -0.86
     become
    -0.85
     getting
    -0.82
     became
    -0.77
    becomes
    -0.76
     gaining
    -0.71
    POSITIVE LOGITS
     habet
    0.76
    SOUNDBITE
    0.67
     Houſe
    0.66
     المعيارى
    0.62
     quæ
    0.62
     ſtand
    0.62
     })}
    0.61
     pleaſure
    0.61
     Theſe
    0.60
     eorum
    0.60
    Activations Density 0.200%

    No Known Activations