© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 3077
    Prev
    Next
    INDEX
    Explanations

    specific scientific terms and concepts, particularly in biology or technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.78
    ↵
    -0.74
     (
    -0.71
    <eos>
    -0.68
    ,
    -0.67
    1
    -0.65
     -
    -0.64
     /
    -0.64
     «
    -0.64
     A
    -0.63
    POSITIVE LOGITS
     propOrder
    1.28
     Efq
    1.14
     myſelf
    1.10
     ―――――
    1.09
     doubtnut
    1.09
     ſever
    1.08
     Anſ
    1.06
     purpoſe
    1.04
     $_(
    1.04
     NDEBUG
    1.03
    Activations Density 0.376%

    No Known Activations