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. 39-GEMMASCOPE-RES-16K
    6. 2930
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and references to self or others in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.63
    GEBURTSDATUM
    -0.62
    aarrggbb
    -0.58
    ➯
    -0.57
     Infórmanos
    -0.56
     cjs
    -0.55
    tvguidetime
    -0.54
    tanleria
    -0.54
    RotationOrder
    -0.54
    Vidite
    -0.54
    POSITIVE LOGITS
    d
    0.81
     d
    0.73
    íd
    0.48
    ’
    0.48
    ed
    0.46
     id
    0.43
    d
    0.43
    ValueStyle
    0.43
    '
    0.43
    éd
    0.41
    Activations Density 0.322%

    No Known Activations