© 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-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 7796
    Prev
    Next
    INDEX
    Explanations

    references to speeches and public addresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ULT
    -0.50
    сё
    -0.50
    lif
    -0.45
     fun
    -0.43
    الحياه
    -0.43
    uns
    -0.42
     all
    -0.41
     offens
    -0.41
     lets
    -0.41
     أب
    -0.40
    POSITIVE LOGITS
     speeches
    1.36
     speech
    1.26
     Speeches
    1.19
     SPEECH
    1.14
     Speech
    1.07
    speech
    1.07
     discurso
    1.02
    Speech
    1.01
     discursos
    0.99
    peech
    0.98
    Activations Density 0.326%

    No Known Activations