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. 15-GEMMASCOPE-RES-16K
    6. 8582
    Prev
    Next
    INDEX
    Explanations

    occurrences of parentheses in code-like structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cæsar
    -0.67
     Efq
    -0.61
     itſelf
    -0.57
    ęty
    -0.56
     MaterialApp
    -0.54
    лтамалар
    -0.53
     newVal
    -0.53
    ();
    -0.52
    ſelf
    -0.52
    escalier
    -0.50
    POSITIVE LOGITS
     مرئيه
    0.76
    enumi
    0.67
     sī
    0.66
    Autoritní
    0.65
    σταση
    0.65
    usermodel
    0.64
    (!__
    0.64
    ActivityCompat
    0.64
     !
    0.64
    OGND
    0.64
    Activations Density 0.058%

    No Known Activations