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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 13482
    Prev
    Next
    INDEX
    Explanations

    key concepts related to scientific measurements and analysis in research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.65
     researches
    -0.59
     GenerationType
    -0.59
    NumOf
    -0.57
     numOf
    -0.56
    InjectMocks
    -0.55
    yntaxException
    -0.54
    izator
    -0.54
    Geplaatst
    -0.52
    ˂
    -0.51
    POSITIVE LOGITS
     nominally
    0.63
     modestly
    0.49
     cleanly
    0.44
     ostensibly
    0.44
     modest
    0.43
     equivalently
    0.42
    ≲
    0.40
    ≳
    0.40
     dizaines
    0.40
     столь
    0.39
    Activations Density 3.866%

    No Known Activations