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. 5236
    Prev
    Next
    INDEX
    Explanations

    responses or updates in a question-and-answer context

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

    Code snippets labeled with "A:" or "Answer:"

    np_acts-logits-general · gemini-2.0-flash

    updates and answers

    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
     ‘
    -0.53
    føre
    -0.53
    ToMany
    -0.51
     normal
    -0.50
     “
    -0.48
    akter
    -0.45
     собою
    -0.45
     dan
    -0.44
    normal
    -0.44
    act
    -0.44
    POSITIVE LOGITS
     متعلقه
    1.16
    expandindo
    0.99
    __":
    
    0.86
    __':
    
    0.85
    Answer
    0.81
     AspNetCore
    0.76
    .*")]
    0.75
    MigrationBuilder
    0.75
    setupUi
    0.74
    थि
    0.71
    Activations Density 0.012%

    No Known Activations