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. 2-GEMMASCOPE-RES-16K
    6. 15192
    Prev
    Next
    INDEX
    Explanations

    contractions and possessives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     referenties
    -0.90
    ^(@)
    -0.81
     doubtnut
    -0.72
     Jefus
    -0.67
     ་་
    -0.66
     الرياضيه
    -0.65
     vetorial
    -0.63
     myſelf
    -0.61
     Forumite
    -0.61
     poffible
    -0.61
    POSITIVE LOGITS
     “
    1.69
     ‘
    1.68
    ’
    1.67
    ”
    1.63
    ’,
    1.59
    ’.
    1.51
    “
    1.50
    .’
    1.50
    ,’
    1.48
    .”
    1.46
    Activations Density 0.413%

    No Known Activations