© 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. 576
    Prev
    Next
    INDEX
    Explanations

    expressions of hope or anticipation

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

    the word "hoping" in various contexts

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

    hoping to or that

    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
    principalColumn
    -0.77
     `<
    -0.50
    ContentAsync
    -0.49
    matchCondition
    -0.48
    Wol
    -0.48
    smithy
    -0.46
    anias
    -0.45
    Yourself
    -0.44
    }{*}{
    -0.44
    WSGI
    -0.44
    POSITIVE LOGITS
     Hopes
    0.98
     hoping
    0.91
     HOPE
    0.89
     hopes
    0.85
     Hoping
    0.84
     hoped
    0.83
     Hope
    0.83
    HOPE
    0.82
    hope
    0.81
     hope
    0.79
    Activations Density 0.020%

    No Known Activations