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. 25-GEMMASCOPE-RES-16K
    6. 4410
    Prev
    Next
    INDEX
    Explanations

    general assessments or statements regarding conditions or trends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     actually
    -1.43
     basically
    -1.40
     essentially
    -1.40
     apparently
    -1.29
     suddenly
    -1.22
     finalement
    -1.22
    actually
    -1.21
     literally
    -1.20
     realmente
    -1.19
     Essentially
    -1.18
    POSITIVE LOGITS
     speaking
    0.71
    ities
    0.66
    speaking
    0.64
     ترین
    0.60
    SequentialGroup
    0.59
    ً
    0.59
     говоря
    0.57
    y
    0.57
    ঃ
    0.57
    стям
    0.56
    Activations Density 0.722%

    No Known Activations