© 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. 16-GEMMASCOPE-RES-16K
    6. 12656
    Prev
    Next
    INDEX
    Explanations

    terms related to conspiracy theories or accusations against specific groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     صوتيه
    -0.38
    ########.
    -0.34
     tyle
    -0.33
    vivid
    -0.32
    wedding
    -0.32
     koc
    -0.31
    лтемелер
    -0.31
     HasFactory
    -0.31
     Ales
    -0.30
     wed
    -0.29
    POSITIVE LOGITS
    +:+
    0.60
     InputDecoration
    0.60
     imperialist
    0.56
     Kissinger
    0.53
    AntiForgeryToken
    0.52
     Geſ
    0.52
    closedir
    0.51
     neoliberal
    0.50
     myſelf
    0.49
     getItemId
    0.49
    Activations Density 0.664%

    No Known Activations