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. 16-GEMMASCOPE-RES-16K
    6. 4944
    Prev
    Next
    INDEX
    Explanations

    phrases related to reading and accessing additional content

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

    Preceding "more", "our", or "Reading"

    np_acts-logits-general · gemini-2.0-flash

    read more or continue reading

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.90
    AsUp
    -0.84
    IsMutable
    -0.82
     betweenstory
    -0.80
     jScrollPane
    -0.79
     Administrativna
    -0.77
     protoimpl
    -0.77
    rrggbb
    -0.76
    __()
    -0.75
     calendriers
    -0.73
    POSITIVE LOGITS
     تضيفلها
    0.76
    Datuak
    0.67
    DispatchToProps
    0.52
    STANDING
    0.51
    basicConfig
    0.50
    ط
    0.49
    ViewById
    0.47
     ای
    0.47
    ÍC
    0.47
    AlterField
    0.46
    Activations Density 0.252%

    No Known Activations