© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 4653
    Prev
    Next
    INDEX
    Explanations

    expressions related to personal identity and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    netinet
    -0.58
     toán
    -0.54
    Datuak
    -0.53
    autogui
    -0.52
    XDECREF
    -0.52
    didSet
    -0.51
    DoubleQuotes
    -0.51
    出版年
    -0.49
    geschäft
    -0.49
     getchar
    -0.48
    POSITIVE LOGITS
     journey
    0.74
     upbringing
    0.69
    principalColumn
    0.64
     decision
    0.64
     relationship
    0.63
     studies
    0.61
    Портал
    0.60
     transition
    0.58
     ++)
    0.57
     search
    0.57
    Activations Density 0.316%

    No Known Activations