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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7-GEMMASCOPE-RES-16K
    6. 2579
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and related phrases emphasizing ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Normdatei
    -1.21
    Personensuche
    -0.93
    DockStyle
    -0.87
    AddAttribute
    -0.74
    RemoveField
    -0.74
     Mep
    -0.73
     ENO
    -0.72
     Khas
    -0.71
    IndentedString
    -0.70
     knobs
    -0.69
    POSITIVE LOGITS
     your
    1.68
    your
    1.51
     Your
    1.47
    YOUR
    1.45
    Your
    1.43
     YOUR
    1.38
     our
    1.20
     votre
    1.18
     own
    1.13
    Votre
    1.10
    Activations Density 0.073%

    No Known Activations