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. 3682
    Prev
    Next
    INDEX
    Explanations

    instances of programming constructs or structures

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

    Code with `for i in range`

    np_acts-logits-general · gemini-2.0-flash

    python for loops with in range

    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
    й
    -0.50
    ''
    -0.49
     '?'
    -0.48
    かし
    -0.45
     tempio
    -0.44
    '
    -0.41
     havi
    -0.40
    Dono
    -0.39
     "
    -0.39
    ;
    -0.39
    POSITIVE LOGITS
     EconPapers
    0.96
     enumerate
    0.90
    }")]
    0.89
     tqdm
    0.87
    зулта
    0.86
    abestanden
    0.85
     range
    0.84
     xrange
    0.82
     ivelany
    0.81
     AssemblyTitle
    0.80
    Activations Density 0.069%

    No Known Activations