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. 14-GEMMASCOPE-RES-16K
    6. 4115
    Prev
    Next
    INDEX
    Explanations

    function calls and method invocations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    leau
    -0.49
    artigen
    -0.45
    setVerticalGroup
    -0.44
     perfect
    -0.44
     ideal
    -0.43
     plank
    -0.43
     seaborn
    -0.43
    arelli
    -0.42
     videre
    -0.42
    droj
    -0.41
    POSITIVE LOGITS
    expandindo
    0.83
     >=",
    0.77
    Autoritní
    0.77
     متعلقه
    0.76
     <<<<<<<<<<<<<<
    0.73
    MENAFN
    0.71
    NameInMap
    0.69
    SuccessListener
    0.69
    ❉
    0.68
    modelBuilder
    0.67
    Activations Density 0.171%

    No Known Activations