© 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. 2048
    Prev
    Next
    INDEX
    Explanations

    the beginning of sentences or sections, specifically the phrase "The."

    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
    AccessorTable
    -0.85
     propOrder
    -0.85
    enumii
    -0.83
    })));
    -0.80
     @"/
    -0.72
     createState
    -0.72
    ']?>
    -0.69
    setVerticalGroup
    -0.68
     protoimpl
    -0.68
    }*/
    -0.66
    POSITIVE LOGITS
    <bos>
    1.08
     Paglinawan
    0.57
    The
    0.56
    UPAC
    0.55
    following
    0.54
    ̀nh
    0.51
     acostumb
    0.51
    setNext
    0.50
     Soro
    0.50
     réve
    0.49
    Activations Density 0.181%

    No Known Activations