© 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-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 16016
    Prev
    Next
    INDEX
    Explanations

    instances of personal pronouns and references to interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.53
    bootstrapcdn
    -0.48
     yyr
    -0.48
    なるほど
    -0.46
    ExtendWith
    -0.46
    styleType
    -0.45
    ValueGeneration
    -0.45
    TagMode
    -0.44
    webElement
    -0.44
    StoryboardSegue
    -0.43
    POSITIVE LOGITS
     gotta
    0.92
     hates
    0.90
     hated
    0.89
     ain
    0.84
     aint
    0.82
     hate
    0.80
     gonna
    0.75
     prolly
    0.74
     don
    0.74
     fucked
    0.74
    Activations Density 0.707%

    No Known Activations