© 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. 27-GEMMASCOPE-RES-16K
    11. 7775
    Prev
    Next
    INDEX
    Explanations

    elements related to discussions and conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/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.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.54
    wußt
    -0.43
    LabelTagHelper
    -0.40
    TagMode
    -0.39
     palk
    -0.38
     AssemblyCompany
    -0.38
     telefónica
    -0.37
    abestanden
    -0.37
     réaliste
    -0.37
     quelquefois
    -0.36
    POSITIVE LOGITS
     episode
    0.62
    Episode
    0.60
     Episode
    0.55
     listeners
    0.51
     episodio
    0.49
    SourceChecksum
    0.49
    episode
    0.49
     episódio
    0.48
    ISODE
    0.48
     episodes
    0.47
    Activations Density 0.092%

    No Known Activations