Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 4405
    Prev
    Next
    INDEX
    Explanations

    uplifting and inspiring themes in texts

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

    "hope" and related terms

    np_acts-logits-general · gemini-2.0-flash

    sense of hope

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nodoc
    -0.56
    batore
    -0.52
    ForValue
    -0.52
    featureID
    -0.52
    siąż
    -0.51
    wydd
    -0.51
    ViewFeatures
    -0.50
    iligung
    -0.50
    uxxxx
    -0.49
     ImportError
    -0.49
    POSITIVE LOGITS
     hope
    2.29
    hope
    1.89
     Hope
    1.83
    Hope
    1.80
     HOPE
    1.74
     hopeful
    1.70
    HOPE
    1.65
     esperanza
    1.55
     hopes
    1.50
    espoir
    1.48
    Activations Density 0.300%

    No Known Activations