© 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. 14-GEMMASCOPE-RES-16K
    11. 8516
    Prev
    Next
    INDEX
    Explanations

    sequences of underscores or placeholders in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.73
    contentLoaded
    -0.63
    出版年
    -0.63
    RenderAtEndOf
    -0.62
    NewUrlParser
    -0.62
     ſind
    -0.61
    EndGlobalSection
    -0.59
     <<<<<<<<<<<<<<
    -0.58
     noDo
    -0.58
     beginnetje
    -0.57
    POSITIVE LOGITS
    _
    0.64
    \_
    0.45
     Athens
    0.42
    marginHorizontal
    0.41
     Frankfurter
    0.39
     Atenas
    0.37
    +"_
    0.37
    ]_
    0.37
    __
    0.36
    _{
    0.36
    Activations Density 0.648%

    No Known Activations