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. 11199
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to survey data handling in Android

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

    appearing with "Adapter"

    np_acts-logits-general · gemini-2.0-flash

    adapter and ViewHolder

    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
    CodeAttribute
    -0.69
    الإنجليزية
    -0.64
     Domes
    -0.55
    bux
    -0.55
     Protección
    -0.54
     SDLK
    -0.52
    acterium
    -0.52
    LOYD
    -0.51
    ].)
    -0.51
     UIAlert
    -0.51
    POSITIVE LOGITS
     adapter
    0.94
    ViewHolder
    0.93
     Adapter
    0.90
    Adapter
    0.86
    adapter
    0.81
     holder
    0.80
     ViewHolder
    0.78
     holders
    0.77
     adapters
    0.73
    holder
    0.72
    Activations Density 0.060%

    No Known Activations