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. 0-GEMMASCOPE-RES-16K
    6. 15032
    Prev
    Next
    INDEX
    Explanations

    repeated mentions of a specific name, particularly the name "Morgan" and words related to physical attributes or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Italij
    -0.81
     miniaturka
    -0.79
     desmotivaciones
    -0.75
     avoient
    -0.73
     plufieurs
    -0.69
     increí
    -0.69
    actéristi
    -0.68
     étoient
    -0.68
     saveiro
    -0.65
     Geiſt
    -0.65
    POSITIVE LOGITS
     Pod
    0.63
     Course
    0.61
     Times
    0.61
    pod
    0.59
     Carter
    0.56
     stick
    0.53
    Pod
    0.52
     Stick
    0.52
     ba
    0.52
     ==
    0.51
    Activations Density 0.258%

    No Known Activations