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. 21-GEMMASCOPE-RES-16K
    6. 15022
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistics related to time or dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FEBRUARY
    -0.58
     April
    -0.57
    Autoritní
    -0.57
    stalt
    -0.55
    Tikang
    -0.54
     APRIL
    -0.54
    April
    -0.53
     disambiguazione
    -0.53
     August
    -0.53
     März
    -0.53
    POSITIVE LOGITS
     June
    0.79
     junho
    0.75
    fromnode
    0.73
    June
    0.71
    六
    0.69
     junio
    0.67
     juin
    0.67
     sixth
    0.66
    sixth
    0.66
     hexagon
    0.65
    Activations Density 0.341%

    No Known Activations