© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 6938
    Prev
    Next
    INDEX
    Explanations

    numerical ratings or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esModule
    -0.42
     IPS
    -0.40
    Montserrat
    -0.40
     lenker
    -0.39
     Kabel
    -0.39
     voodoo
    -0.39
    DotNetBar
    -0.38
     Colchester
    -0.38
     Monique
    -0.36
    期刊论文
    -0.36
    POSITIVE LOGITS
     Hobbit
    1.05
     Gandalf
    1.03
     Tolkien
    1.02
     hobbit
    0.97
     Arag
    0.84
     Bil
    0.83
     Fro
    0.79
     LOT
    0.79
    olkien
    0.78
     Middle
    0.77
    Activations Density 0.122%

    No Known Activations