© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 6012
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "pitch" in mechanical and engineering contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]")]
    -0.54
    principalColumn
    -0.54
     resourceCulture
    -0.53
     CanadaChoose
    -0.51
    躇
    -0.48
     المعيارى
    -0.47
    喱
    -0.47
    tagHelperRunner
    -0.46
     findOne
    -0.45
     Plug
    -0.44
    POSITIVE LOGITS
     alliance
    0.85
     allies
    0.84
     alliances
    0.79
     Alliance
    0.79
    Alliance
    0.75
     Allies
    0.68
    alliance
    0.67
     ally
    0.60
     allied
    0.60
     aliados
    0.58
    Activations Density 0.098%

    No Known Activations