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. 8717
    Prev
    Next
    INDEX
    Explanations

    frequent references to the quantity or abundance of things

    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
     Meksiku
    -0.89
    Datuak
    -0.85
    aarrggbb
    -0.79
    __()
    -0.79
    >*/
    -0.77
    IUrlHelper
    -0.77
    DoubleQuotes
    -0.76
     @"/
    -0.73
    }")
    
    -0.72
     Rine
    -0.72
    POSITIVE LOGITS
     lots
    1.79
     Lots
    1.63
    Lots
    1.58
     LOTS
    1.46
    lots
    1.39
     plenty
    1.23
    plenty
    1.14
     Plenty
    1.10
    Plenty
    0.97
     tons
    0.82
    Activations Density 0.057%

    No Known Activations