© 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. 14309
    Prev
    Next
    INDEX
    Explanations

    terms related to licensing and software specifications

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

    Uncommon or foreign words and symbols

    np_acts-logits-general · gemini-2.0-flash

    Jarzynski relation lost profits neural tube

    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
     GENERATED
    -0.57
    ('../../
    -0.47
    ('../../../
    -0.45
    cuadro
    -0.45
    (['/
    -0.45
     linkovi
    -0.44
    Yess
    -0.43
    intracht
    -0.43
    datab
    -0.42
    Географи
    -0.42
    POSITIVE LOGITS
    WebVitals
    1.23
    BufferException
    0.98
    TagMode
    0.90
    TargetException
    0.83
     الدولى
    0.78
    脚注の使い方
    0.74
     utafitiHapana
    0.72
    تقاوى
    0.70
     MainAxisSize
    0.70
    AxisAlignment
    0.70
    Activations Density 1.761%

    No Known Activations