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. 7-GEMMASCOPE-RES-16K
    6. 6161
    Prev
    Next
    INDEX
    Explanations

    references to downtown areas and their associated developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     given
    -0.44
    器
    -0.42
    บัติ
    -0.42
    given
    -0.41
    consin
    -0.41
     remercier
    -0.40
     Nascimento
    -0.40
     وتسجيلات
    -0.40
    orca
    -0.40
     beweg
    -0.39
    POSITIVE LOGITS
     downtown
    1.16
    Downtown
    0.99
    downtown
    0.99
     Downtown
    0.93
     resourceCulture
    0.82
     Roskov
    0.79
     '\\;'
    0.79
    UnusedPrivate
    0.77
     jScrollPane
    0.77
    DockStyle
    0.73
    Activations Density 0.141%

    No Known Activations