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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 8817
    Prev
    Next
    INDEX
    Explanations

    references to "account" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \{\\
    -0.43
    onAttach
    -0.43
    🏾
    -0.42
    🏿
    -0.42
    pretty
    -0.42
    RTLU
    -0.41
     Acon
    -0.40
    󠁿
    -0.40
    poor
    -0.39
    🏻
    -0.39
    POSITIVE LOGITS
    ancy
    0.67
     receivable
    0.59
     getAccount
    0.58
    rements
    0.55
     Account
    0.50
    ants
    0.47
     Compte
    0.46
    accountId
    0.46
     Konto
    0.45
    stateMutability
    0.43
    Activations Density 0.103%

    No Known Activations