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. 4888
    Prev
    Next
    INDEX
    Explanations

    specific mathematical concepts and their applications

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

    Followed by clauses or phrases

    np_acts-logits-general · gemini-2.0-flash

    introduce a concept

    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
    ัติ
    -0.80
    iented
    -0.72
    oa̍t
    -0.71
    fromnode
    -0.70
    WebElementEntity
    -0.70
     unknownFields
    -0.68
    oglobin
    -0.66
     NSCoder
    -0.66
    
    -0.65
    orari
    -0.65
    POSITIVE LOGITS
    NoSuchAlgorithm
    0.56
    prepareStatement
    0.48
     GetEnumerator
    0.44
    חור
    0.43
    гур
    0.42
     oneself
    0.42
     sebelumnya
    0.42
     would
    0.42
     įva
    0.40
    README
    0.39
    Activations Density 0.431%

    No Known Activations