© 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. 24-GEMMASCOPE-RES-16K
    11. 2096
    Prev
    Next
    INDEX
    Explanations

    various levels of intensity or emphasis in text

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

    followed by diacritics/numerals

    np_acts-logits-general · gemini-2.0-flash

    ṣ or ḍ followed by numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     profundos
    -0.42
     gyere
    -0.37
     verduras
    -0.37
     dieną
    -0.36
     rápidas
    -0.35
     enemmän
    -0.35
     cref
    -0.35
     oscuros
    -0.35
     jegy
    -0.35
     complètes
    -0.35
    POSITIVE LOGITS
     تضيفلها
    0.75
     oneself
    0.72
    Ведь
    0.71
    )».
    0.71
    '}),
    0.68
    tised
    0.67
    Tikang
    0.66
     ),
    0.65
    +:+
    0.64
    RenderAtEndOf
    0.64
    Activations Density 0.096%

    No Known Activations