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. 3-GEMMASCOPE-RES-16K
    6. 6075
    Prev
    Next
    INDEX
    Explanations

    mentions of specific web API-related keywords and relevant statistical terms in the context of research, particularly those associated with Robins

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portail
    -0.84
     Decl
    -0.72
     Bautista
    -0.70
    ibatkan
    -0.67
    gazione
    -0.66
    তথ্যসূত্র
    -0.64
     Ares
    -0.64
     Louie
    -0.64
    /**
    -0.64
    Louie
    -0.64
    POSITIVE LOGITS
     pension
    0.79
     cory
    0.73
     Colts
    0.73
     Sting
    0.72
    triangleq
    0.72
     Benjam
    0.72
     Pension
    0.71
     Fior
    0.71
     Cory
    0.71
     parallax
    0.70
    Activations Density 1.394%

    No Known Activations