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. 8-GEMMASCOPE-RES-16K
    6. 8028
    Prev
    Next
    INDEX
    Explanations

    verbs and their forms that indicate capability or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    –¿
    -0.66
    eradish
    -0.65
    FormTagHelper
    -0.62
    Beijinhos
    -0.59
    aimana
    -0.59
    twe
    -0.58
    -¿
    -0.58
    thaw
    -0.57
     MenuView
    -0.57
     Efq
    -0.57
    POSITIVE LOGITS
     its
    1.11
    Its
    1.08
     Its
    1.05
    它
    1.00
    它的
    1.00
     它
    0.93
     itself
    0.86
    它是
    0.81
    因为它
    0.81
     Itself
    0.76
    Activations Density 0.651%

    No Known Activations