Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 7730
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and keywords associated with events, flags, and input/output operations

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

    Bitwise operations and flag settings

    np_acts-logits-general · gemini-2.0-flash

    bitwise operations and flags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    انظر
    -0.56
    談社
    -0.53
    Šaltiniai
    -0.49
     carbone
    -0.47
    MethodImpl
    -0.44
    terno
    -0.43
    athus
    -0.43
    athed
    -0.42
     Lorenzo
    -0.42
    SequentialGroup
    -0.41
    POSITIVE LOGITS
     CreateTagHelper
    0.74
    MergeFrom
    0.59
     betweenstory
    0.58
    clusal
    0.58
    TypedDataSet
    0.54
    iastes
    0.54
    PickerController
    0.52
    '|
    0.50
    NUMX
    0.50
     $_"
    0.50
    Activations Density 0.297%

    No Known Activations