© 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. 5877
    Prev
    Next
    INDEX
    Explanations

    instances of the term "generic" in various 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
    OGND
    -0.59
    PYX
    -0.54
    IntoConstraints
    -0.54
     CreateTagHelper
    -0.54
    ⤹
    -0.53
    SequentialGroup
    -0.52
    entyfik
    -0.52
    󠁢
    -0.52
     estekak
    -0.49
    writeHead
    -0.49
    POSITIVE LOGITS
     Sciences
    0.80
     generic
    0.77
     ing
    0.75
     Ing
    0.71
    architecture
    0.69
     architecture
    0.69
     Generic
    0.68
    generic
    0.67
     sciences
    0.66
    Generic
    0.65
    Activations Density 0.094%

    No Known Activations