© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 9197
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to coding and documentation

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

    Code snippets or code-related terms

    np_acts-logits-general · gemini-2.0-flash

    Protocol Buffers and code structures

    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
    NullCheck
    -0.59
    andExpect
    -0.57
    __(/*!
    -0.56
     (!$
    -0.55
     OkHttpClient
    -0.54
     kasarigan
    -0.52
    Referințe
    -0.52
    flashdata
    -0.52
    readystatechange
    -0.52
    lims
    -0.51
    POSITIVE LOGITS
     createSlice
    0.82
     transférez
    0.63
    AsUp
    0.60
     estekak
    0.57
    Външни
    0.56
    hoeddwyd
    0.56
    Derbyniad
    0.54
    ollectionView
    0.53
    jspx
    0.52
    Zdroj
    0.50
    Activations Density 0.260%

    No Known Activations