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. 12112
    Prev
    Next
    INDEX
    Explanations

    terms and references associated with laboratory methodologies and biomedical contexts

    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
     Nim
    -0.79
     Lloyd
    -0.75
     kwargs
    -0.70
    Lenny
    -0.69
     Tulane
    -0.69
     Jekyll
    -0.67
     FEN
    -0.67
     Alejandro
    -0.67
     برانيه
    -0.66
    jle
    -0.66
    POSITIVE LOGITS
     Tamb
    0.93
     cassettes
    0.90
     Kamb
    0.87
    NamedQuery
    0.85
     GUS
    0.83
     Theron
    0.83
     Mercer
    0.82
     Herbst
    0.81
     HRC
    0.81
    fficacy
    0.81
    Activations Density 1.770%

    No Known Activations