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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15184
    Prev
    Next
    INDEX
    Explanations

    references to dynamic linking and compilation processes in programming contexts

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

    Code compilation or linking

    np_acts-logits-general · gemini-2.0-flash

    compile or link code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    +#+#
    -0.59
     bellezza
    -0.45
    autogui
    -0.44
    ########.
    -0.44
    AndEndTag
    -0.43
    MENAFN
    -0.41
    ControllerTest
    -0.41
     føl
    -0.40
     <>",
    -0.40
    matchCondition
    -0.38
    POSITIVE LOGITS
     jadx
    0.56
    脚注の使い方
    0.53
    ClCompile
    0.52
    sizeCache
    0.49
    webpack
    0.48
    WebpackPlugin
    0.48
    finished
    0.48
     AssemblyTitle
    0.47
     beginnetje
    0.46
    rawDesc
    0.45
    Activations Density 0.737%

    No Known Activations