Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10505
    Prev
    Next
    INDEX
    Explanations

    statements expressing uncertainty or indecision

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

    Contractions and possessives

    np_acts-logits-general · gemini-2.0-flash

    always been good

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ”
    -2.29
     “
    -2.24
    ’”
    -2.19
    ’.
    -2.17
    .’
    -2.13
    ’,
    -2.12
    ’)
    -2.09
     ‘
    -2.09
    ”.
    -2.08
    ,’
    -2.07
    POSITIVE LOGITS
    '
    1.91
     "
    1.89
     '
    1.78
    。"
    1.71
    "
    1.49
     ("
    1.49
    '"
    1.43
    ..."
    1.39
     "'
    1.35
    :"
    1.34
    Activations Density 0.701%

    No Known Activations