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. 10-GEMMASCOPE-RES-16K
    6. 12272
    Prev
    Next
    INDEX
    Explanations

    programming syntax related to lists and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ItemBackground
    -0.66
    Spoljašnje
    -0.53
    transmitters
    -0.52
    ์ตูน
    -0.52
    agrama
    -0.50
    ersham
    -0.49
    bolts
    -0.49
     lumière
    -0.49
    Gruss
    -0.49
     crdi
    -0.48
    POSITIVE LOGITS
     []:
    4.76
    ynb
    1.08
     مشين
    1.06
    migrationBuilder
    0.95
     <<<<<<<<<<<<<<
    0.86
    awtextra
    0.82
     snippetHide
    0.80
    .*")]
    0.78
     "..\..\..\
    0.77
    ThroughAttribute
    0.77
    Activations Density 0.014%

    No Known Activations