© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 14398
    Prev
    Next
    INDEX
    Explanations

    negations and words indicating doubt or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UrlResolution
    -0.71
    OGND
    -0.66
    PerformLayout
    -0.64
    bootstrapcdn
    -0.61
    DIPSETTING
    -0.61
    SerializedSize
    -0.60
    enterOuterAlt
    -0.58
     resourceCulture
    -0.56
     صوتيه
    -0.56
    RenderAtEndOf
    -0.56
    POSITIVE LOGITS
    <code>
    0.52
     forum
    0.43
     @
    0.41
     Discourse
    0.38
     topic
    0.38
    =“
    0.36
     фору
    0.35
     …
    0.34
    ■■
    0.33
     Aso
    0.33
    Activations Density 0.202%

    No Known Activations