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-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 10542
    Prev
    Next
    INDEX
    Explanations

    expressions related to self-referential subject pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verwijspagina
    -0.54
    IsMutable
    -0.53
    charCode
    -0.51
     InputDecoration
    -0.51
    inSlope
    -0.50
    GenerationType
    -0.46
    AccessorTable
    -0.46
    ">//
    -0.44
    Tracce
    -0.43
    קישורים
    -0.42
    POSITIVE LOGITS
     congratulated
    0.36
    querySelectorAll
    0.36
     suic
    0.36
     apropi
    0.35
    Complaints
    0.35
     aventura
    0.35
     amuse
    0.35
     familiarize
    0.34
     prostitute
    0.34
     suicide
    0.33
    Activations Density 0.084%

    No Known Activations