Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 8085
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to progression and limits

    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
    usercontent
    -0.32
    pushFollow
    -0.32
    Att
    -0.30
    <%@
    -0.29
     Gesch
    -0.29
     Att
    -0.28
    Æ
    -0.28
    "}"
    -0.28
     deven
    -0.27
     SES
    -0.27
    POSITIVE LOGITS
     far
    2.47
    far
    2.09
     farthest
    1.89
     farther
    1.85
     furthest
    1.80
    Far
    1.76
     Far
    1.68
     jauh
    1.65
     далеко
    1.55
     FAR
    1.52
    Activations Density 0.354%

    No Known Activations