© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 15171
    Prev
    Next
    INDEX
    Explanations

    elements related to programming and technical documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Statements, quotations, or blurbs

    np_acts-logits-general · gemini-2.0-flash

    says or stating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ImageContext
    -0.82
    __":
    -0.79
     pleaſure
    -0.72
    __':
    -0.69
    IntoConstraints
    -0.67
    __":
    -0.67
    __':
    -0.67
     purpoſe
    -0.67
    kháu
    -0.64
     faſt
    -0.64
    POSITIVE LOGITS
     says
    1.15
     saying
    1.00
     stating
    0.92
    says
    0.90
     stated
    0.82
     tertulis
    0.79
     say
    0.79
     Says
    0.78
     SAYS
    0.75
     it
    0.74
    Activations Density 0.329%

    No Known Activations