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. 4-GEMMASCOPE-RES-16K
    6. 15815
    Prev
    Next
    INDEX
    Explanations

    instances of the word "call" and its derivatives in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.75
     Marien
    -0.71
    Endian
    -0.71
    wendi
    -0.70
    PushMatrix
    -0.67
    PyExc
    -0.65
     Moray
    -0.62
    djangoproject
    -0.62
    acen
    -0.61
     ergo
    -0.61
    POSITIVE LOGITS
     call
    2.38
     calls
    2.19
     CALL
    2.11
     Call
    2.06
     calling
    2.05
     Calls
    2.02
    call
    2.02
    Call
    1.99
     Calling
    1.93
    CALL
    1.90
    Activations Density 0.128%

    No Known Activations