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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 6876
    Prev
    Next
    INDEX
    Explanations

    information related to personal and contact details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    names and personal identity information (first names, last names, email addresses, and related fields).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ///</
    -0.32
     gelten
    -0.32
    ovac
    -0.30
    沿革
    -0.29
     estekak
    -0.29
    μι
    -0.28
    titur
    -0.28
     Rew
    -0.28
    typeDefinition
    -0.28
     hidráulica
    -0.28
    POSITIVE LOGITS
     surname
    1.63
     name
    1.45
     surnames
    1.40
     names
    1.36
     Name
    1.32
    姓名
    1.31
     prénom
    1.30
    姓
    1.27
     Names
    1.26
     firstName
    1.26
    Activations Density 0.318%

    No Known Activations