© 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. 5081
    Prev
    Next
    INDEX
    Explanations

    references to alternative options or alternatives 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
    fjspx
    -0.49
    tagext
    -0.47
    luß
    -0.46
    iança
    -0.44
    Inggris
    -0.42
     lips
    -0.42
    zydent
    -0.42
    #+#
    -0.41
    VersionUID
    -0.41
    TypedDataSet
    -0.41
    POSITIVE LOGITS
     alternative
    4.25
    alternative
    3.91
     Alternative
    3.72
    Alternative
    3.72
     ALTERNATIVE
    3.47
     alternatives
    3.36
     alternativa
    3.22
     alternate
    3.13
     alternativo
    2.98
     alternatif
    2.97
    Activations Density 0.126%

    No Known Activations