© 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. 6877
    Prev
    Next
    INDEX
    Explanations

    patterns related to method declarations and returns in programming

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

    Code snippets with unusual formatting

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by of

    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
    errHandler
    -0.80
     فريبيس
    -0.74
    ⓧ
    -0.73
     ivelany
    -0.72
    ]})
    -0.72
    }))
    -0.71
    AndEndTag
    -0.69
    AddTagHelper
    -0.69
    ]))
    -0.68
    SequentialGroup
    -0.67
    POSITIVE LOGITS
     οποίο
    0.56
    avajillas
    0.46
     Dunlop
    0.45
     trom
    0.44
    álogo
    0.42
    BarButtonItem
    0.42
    JAXB
    0.42
    Filmographie
    0.42
    ایای
    0.41
     remp
    0.41
    Activations Density 0.027%

    No Known Activations