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. 1427
    Prev
    Next
    INDEX
    Explanations

    code structures related to buffers and memory management

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

    Code snippets with brackets and semicolons

    np_acts-logits-general · gemini-2.0-flash

    variable declarations and code punctuation

    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
    aarrggbb
    -1.23
     betweenstory
    -1.05
    ValueStyle
    -0.93
    LookAnd
    -0.88
     ComVisible
    -0.86
    󠁴
    -0.80
     الحره
    -0.80
    UnsafeEnabled
    -0.79
    InstrumentedTest
    -0.78
    GOTREF
    -0.76
    POSITIVE LOGITS
     already
    0.46
     uParam
    0.45
    thyl
    0.44
    าศ
    0.44
    FlowLayout
    0.43
     drawn
    0.43
    tter
    0.41
    제
    0.41
     vides
    0.41
    عود
    0.41
    Activations Density 0.136%

    No Known Activations