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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 5521
    Prev
    Next
    INDEX
    Explanations

    references to specific locations, especially towns and regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.86
    Tikang
    -0.80
     pinulongan
    -0.79
     محفوظة
    -0.77
     nahilalakip
    -0.76
    <unused41>
    -0.75
    <unused43>
    -0.75
    <unused74>
    -0.75
    <unused1>
    -0.75
    <pad>
    -0.75
    POSITIVE LOGITS
     således
    0.32
    </td>
    0.28
     verwacht
    0.28
    』
    0.28
    yntaxException
    0.26
    Académie
    0.25
     oczywiście
    0.25
     tilbake
    0.25
     While
    0.25
     jeugd
    0.25
    Activations Density 0.441%

    No Known Activations