Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 15207
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate benefits and detriments_related to financial or economic transactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.62
     AppCompat
    -0.56
    typeorm
    -0.52
    "?>
    -0.51
    iremos
    -0.49
     vVar
    -0.48
     Umgang
    -0.48
    anking
    -0.47
    Polly
    -0.47
     solidity
    -0.47
    POSITIVE LOGITS
    expandindo
    0.53
    IndentedString
    0.52
    DeleteBehavior
    0.52
     Roskov
    0.51
     others
    0.50
    jería
    0.49
    OFFICE
    0.47
     nargin
    0.47
    Itoa
    0.47
    ksiä
    0.47
    Activations Density 0.380%

    No Known Activations