© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 16057
    Prev
    Next
    INDEX
    Explanations

    instances of numerical data and their relationships in text

    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
     disambiguazione
    -0.81
    parsedMessage
    -0.81
    SharedCtor
    -0.75
    stateMutability
    -0.69
    __':
    -0.69
    IBOutlet
    -0.68
     ostavi
    -0.68
    tagext
    -0.66
    principalTable
    -0.65
    DispatchToProps
    -0.64
    POSITIVE LOGITS
    AddAttribute
    0.48
     gynhyrchwyd
    0.47
     hadapan
    0.42
    wearing
    0.40
     aikana
    0.40
    <sub>
    0.39
    Jîn
    0.39
    enumii
    0.39
    //{
    0.38
     accla
    0.35
    Activations Density 0.258%

    No Known Activations