© 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. 2516
    Prev
    Next
    INDEX
    Explanations

    grammatical constructions that indicate causality or actions taken by subjects

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

    Text after headings or introductions

    np_acts-logits-general · gemini-2.0-flash

    technical summaries and reports

    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
     therefrom
    -1.15
     thereof
    -0.99
    parsedMessage
    -0.97
    }$.\\
    -0.96
    tdessen
    -0.91
     thereon
    -0.87
    __':
    -0.86
     thence
    -0.85
    });*/
    -0.84
    '])->
    -0.84
    POSITIVE LOGITS
     هنگ
    0.55
    MERCIAL
    0.53
    hermosa
    0.50
    Denomin
    0.49
    seamnă
    0.49
     BufferedReader
    0.45
    rededor
    0.44
    éreo
    0.44
    vily
    0.44
    ^(@)
    0.43
    Activations Density 1.498%

    No Known Activations