© 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. 15-GEMMASCOPE-RES-16K
    11. 2193
    Prev
    Next
    INDEX
    Explanations

    proper names and specific entities related to academic citations or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endphp
    -0.68
    rungsseite
    -0.63
     상세
    -0.55
     kasarigan
    -0.49
    KommentareTeilen
    -0.48
     EconPapers
    -0.48
     inspiração
    -0.48
     autorytatywna
    -0.47
     CanadaChoose
    -0.47
     AssemblyCompany
    -0.46
    POSITIVE LOGITS
     ivelany
    0.47
    ellido
    0.45
    &+
    0.39
     doPost
    0.39
    &__
    0.39
     AppCompatTheme
    0.38
    jMenuItem
    0.38
    ModelSerializer
    0.38
     vnode
    0.37
     &_
    0.37
    Activations Density 0.471%

    No Known Activations