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. 4292
    Prev
    Next
    INDEX
    Explanations

    phrases involving inclusion or membership in a context

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

    Comes after "Q:" or "if"

    np_acts-logits-general · gemini-2.0-flash

    archaic French and English

    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
     
    -0.54
     “
    -0.52
    bau
    -0.48
     pek
    -0.47
    zmán
    -0.47
    var
    -0.47
     var
    -0.46
     huge
    -0.46
    dig
    -0.46
     many
    -0.46
    POSITIVE LOGITS
     prêtres
    0.80
     noDo
    0.79
     feroit
    0.78
     auroit
    0.78
     quæ
    0.74
     obstante
    0.74
    theless
    0.74
     withal
    0.72
     ſtate
    0.72
     enfans
    0.72
    Activations Density 0.732%

    No Known Activations