© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 8946
    Prev
    Next
    INDEX
    Explanations

    references to accounts and account management terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /*
    -0.59
     esimer
    -0.56
     colorir
    -0.54
     vijf
    -0.53
    vages
    -0.52
     Weird
    -0.50
     Wolfe
    -0.49
     Vars
    -0.48
     Welding
    -0.48
    Wolfe
    -0.48
    POSITIVE LOGITS
    Account
    0.81
     Account
    0.80
     account
    0.76
     ACCOUNT
    0.75
     getAccount
    0.75
    ACCOUNT
    0.74
     Konto
    0.69
    getAccount
    0.68
    account
    0.65
     accounts
    0.61
    Activations Density 0.104%

    No Known Activations