© 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. 7840
    Prev
    Next
    INDEX
    Explanations

    identifiers and discussions related to online communities, particularly forums and anonymity

    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
     Infórmanos
    -0.40
    Errorf
    -0.33
    ftagPool
    -0.32
    itmen
    -0.29
     😂
    -0.29
     CanadaChoose
    -0.28
     widely
    -0.28
    😂
    -0.28
     nonatomic
    -0.28
     🤷
    -0.28
    POSITIVE LOGITS
     anon
    0.71
     Anon
    0.66
    Anon
    0.65
    Vidite
    0.63
     anonymous
    0.59
     Trips
    0.58
     Anonymous
    0.56
    Trips
    0.56
    trips
    0.55
    ">>
    0.52
    Activations Density 0.341%

    No Known Activations