© 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. 1507
    Prev
    Next
    INDEX
    Explanations

    terms related to research studies and methodologies

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

    references to research methodology and findings

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

    previous or current research/study

    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
     later
    -0.91
     initially
    -0.87
    平时
    -0.80
    later
    -0.80
     hereafter
    -0.79
    GEBURTSDATUM
    -0.76
     kés
    -0.76
     myö
    -0.75
    Initially
    -0.72
     ultimately
    -0.71
    POSITIVE LOGITS
    protoimpl
    0.56
     incarnation
    0.53
    шня
    0.49
    setValues
    0.49
     debacle
    0.49
    itisation
    0.48
    ತ್ತು
    0.48
    шні
    0.47
     iterations
    0.45
     iteration
    0.45
    Activations Density 0.207%

    No Known Activations