© 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. 11-GEMMASCOPE-RES-16K
    11. 4980
    Prev
    Next
    INDEX
    Explanations

    phrases expressing assistance and support within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ContentAsync
    -0.55
    ">//
    -0.54
     ivelany
    -0.49
    MessageTagHelper
    -0.48
     anſ
    -0.47
     Anſ
    -0.46
    AddTagHelper
    -0.43
     ujednoznacz
    -0.41
    IsContent
    -0.41
    +#+#
    -0.41
    POSITIVE LOGITS
     unavoidable
    0.88
     inescapable
    0.86
     inevitable
    0.81
     unavoid
    0.71
     inevit
    0.69
    どうしても
    0.63
     inevitably
    0.62
     irresistible
    0.59
     uncontrollable
    0.59
    忍不住
    0.57
    Activations Density 0.435%

    No Known Activations