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. 10-GEMMASCOPE-RES-16K
    6. 13201
    Prev
    Next
    INDEX
    Explanations

    specific terms related to biochemical processes and analysis in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     and
    -0.59
     mergeFrom
    -0.57
     hyö
    -0.50
    そうで
    -0.49
    ंध
    -0.48
     or
    -0.48
    teto
    -0.48
     chiffres
    -0.47
    IDADE
    -0.46
     négy
    -0.45
    POSITIVE LOGITS
     pinulongan
    0.83
     kasarigan
    0.77
    Alike
    0.77
     alike
    0.76
    TargetException
    0.75
    ंदीखरीदारी
    0.73
     respectively
    0.72
     autorytatywna
    0.70
    Portale
    0.69
     respectivamente
    0.69
    Activations Density 1.415%

    No Known Activations