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. 12-GEMMASCOPE-RES-16K
    6. 7389
    Prev
    Next
    INDEX
    Explanations

    the beginning of diverse sections, perhaps indicating the start of separate topics or data points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.89
    fjspx
    -0.64
    SourceChecksum
    -0.61
     CreateTagHelper
    -0.61
    webElement
    -0.58
    BASEPATH
    -0.58
    :+:
    -0.58
    parsedMessage
    -0.57
    GOTREF
    -0.56
    tabular
    -0.55
    POSITIVE LOGITS
     climatique
    0.60
    انيف
    0.57
     humaines
    0.56
    Datuak
    0.55
     quieras
    0.52
     ferroviaire
    0.51
     gerais
    0.50
     demais
    0.50
     partecipazione
    0.50
     acaso
    0.49
    Activations Density 0.065%

    No Known Activations