© 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. 5960
    Prev
    Next
    INDEX
    Explanations

    various punctuation marks and delimiters used in data formatting and programming syntax

    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
    StoryboardSegue
    -0.76
    UnusedPrivate
    -0.68
    ']").
    -0.57
     doInBackground
    -0.56
    "):
    -0.54
    endphp
    -0.54
    uxxxx
    -0.54
    __':
    -0.53
    '])->
    -0.52
     */,
    -0.52
    POSITIVE LOGITS
    MessageOf
    0.42
     <<<<<<<<<<<<<<
    0.41
    centroids
    0.40
    崭
    0.39
    ("[
    0.39
     réc
    0.39
    (":
    0.38
     equip
    0.38
     '{@
    0.38
    Seni
    0.38
    Activations Density 0.211%

    No Known Activations