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. 1481
    Prev
    Next
    INDEX
    Explanations

    code structures and function definitions, particularly focusing on return statements

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

    Methods, especially getter methods

    np_acts-logits-general · gemini-2.0-flash

    video cameras and radio

    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
    bootstrapcdn
    -0.79
    Xna
    -0.53
    存于互联网档案馆
    -0.53
     ver
    -0.52
     كرة
    -0.52
    rapeau
    -0.50
    DTD
    -0.50
     án
    -0.49
     مرئيه
    -0.49
    AddTagHelper
    -0.48
    POSITIVE LOGITS
     démocr
    0.69
     réve
    0.59
     noires
    0.58
     vêtement
    0.54
     paž
    0.54
     fjor
    0.54
     circonstances
    0.53
     thérape
    0.53
     kasarigan
    0.53
     malheure
    0.52
    Activations Density 0.020%

    No Known Activations