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. 11-GEMMASCOPE-RES-16K
    6. 14031
    Prev
    Next
    INDEX
    Explanations

    terms related to biological processes and their regulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.99
     AssemblyCulture
    -0.59
    ValueStyle
    -0.52
    TypedDataSet
    -0.50
    ItemBackground
    -0.50
     AssemblyTitle
    -0.49
    ftagPool
    -0.48
     semej
    -0.47
     Ar
    -0.45
    }{}
    -0.45
    POSITIVE LOGITS
     purpoſe
    0.84
     EconPapers
    0.80
     makeStyles
    0.80
     Efq
    0.79
     Perfon
    0.77
     itſelf
    0.77
     Monfieur
    0.76
     Houſe
    0.74
     gonzález
    0.74
     myſelf
    0.72
    Activations Density 2.764%

    No Known Activations