© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 898
    Prev
    Next
    INDEX
    Explanations

    claims regarding ownership or authoritative roles in contexts with specificity

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

    Occurrences before punctuation

    np_acts-logits-general · gemini-2.0-flash

    ends sentences or lists

    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
    脚注の使い方
    -1.08
     дописавши
    -1.05
    tvguidetime
    -1.03
     CURIAM
    -1.02
     مشين
    -1.00
    MemoryWarning
    -0.93
    دانشنامهٔ
    -0.92
    awtextra
    -0.92
     Chwiliwch
    -0.90
     الرياضيه
    -0.90
    POSITIVE LOGITS
    ),
    1.06
     ),
    0.84
     –,
    0.73
    );
    0.71
    ;
    0.69
     etc
    0.68
    ],
    0.67
    }),
    0.66
    )、
    0.65
    },
    0.65
    Activations Density 0.758%

    No Known Activations