© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5876
    Prev
    Next
    INDEX
    Explanations

    pronouns and their usage in various contexts

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

    "can see" or "can tell" phrases

    np_acts-logits-general · gemini-2.0-flash

    as you can see/tell

    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
    LookAnd
    -1.00
     resourceCulture
    -0.95
     nakalista
    -0.92
    tagHelperRunner
    -0.77
    توض
    -0.75
    homonymie
    -0.74
    utilisons
    -0.73
    featureID
    -0.71
    новниш
    -0.71
    TagHelper
    -0.70
    POSITIVE LOGITS
    "]').
    0.48
    )))))
    0.48
    ')):
    0.47
    ))]
    0.45
    =").
    0.44
     infer
    0.44
    ')],
    0.43
    ')).
    0.42
    })]
    0.42
    ')));
    0.41
    Activations Density 0.278%

    No Known Activations