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. 18-GEMMASCOPE-RES-16K
    6. 14338
    Prev
    Next
    INDEX
    Explanations

    code-related terminology and programming structures relevant to functions

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

    C++ or Java code snippets

    np_acts-logits-general · gemini-2.0-flash

    sorting integer arrays

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الرياضيه
    -0.58
     [][]
    -0.54
    getline
    -0.50
     [['
    -0.49
     quadruple
    -0.49
    zzano
    -0.48
    [][]
    -0.47
    CodedInputStream
    -0.47
    矩阵
    -0.47
    Multiline
    -0.46
    POSITIVE LOGITS
    Бахар
    0.68
     للمعارف
    0.58
    antMatchers
    0.58
    AndEndTag
    0.57
     defaultstate
    0.56
     intervalo
    0.55
     MessageBoxIcon
    0.54
     Gaps
    0.53
     INTERVAL
    0.53
    र्ट
    0.52
    Activations Density 0.513%

    No Known Activations