© 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. 33-GEMMASCOPE-RES-16K
    11. 11642
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns and collective references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.84
     kasarigan
    -0.74
     CreateTagHelper
    -0.60
     Majefty
    -0.59
     lenker
    -0.59
    Handlung
    -0.56
    ↹
    -0.56
     femininas
    -0.55
     ſche
    -0.55
     ligiloj
    -0.55
    POSITIVE LOGITS
     admire
    0.78
     thank
    0.74
     owe
    0.72
     admires
    0.71
     grateful
    0.70
     thankful
    0.68
     Thank
    0.67
     admired
    0.65
     appreciate
    0.64
     owes
    0.64
    Activations Density 0.218%

    No Known Activations