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. 5-GEMMASCOPE-RES-16K
    6. 9082
    Prev
    Next
    INDEX
    Explanations

    various aspects or properties of objects in a systematic or technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     linkovi
    -0.83
    WithIOException
    -0.78
    aarrggbb
    -0.76
    Népesség
    -0.65
    ViewStyle
    -0.63
     <",
    -0.59
    Демографія
    -0.58
    ніципа
    -0.56
     Vole
    -0.55
    Zunanje
    -0.55
    POSITIVE LOGITS
     JpaRepository
    0.61
    <tr>
    0.60
    ↵↵
    0.59
     onCreateView
    0.56
    AxisAlignment
    0.54
     dermed
    0.52
     %>%
    0.51
     passagers
    0.51
     économiques
    0.51
    <eos>
    0.50
    Activations Density 0.031%

    No Known Activations