© 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. 20-GEMMASCOPE-RES-16K
    11. 7803
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and mathematical symbols in a formal text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Unusual punctuation and symbols

    np_acts-logits-general · gemini-2.0-flash

    closing punctuation for code or math

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -0.58
     =
    -0.56
     +
    -0.51
     form
    -0.49
     >=
    -0.49
     mid
    -0.48
    ...
    -0.48
    -
    -0.48
     par
    -0.47
     offers
    -0.47
    POSITIVE LOGITS
     مشين
    1.01
    writeFieldEnd
    0.92
    __':
    0.92
    __":
    0.88
    DockStyle
    0.86
    ]")]
    0.86
     fallu
    0.82
    }';
    0.81
     الحره
    0.80
    __":
    0.80
    Activations Density 0.495%

    No Known Activations