© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 6383
    Prev
    Next
    INDEX
    Explanations

    markers indicating the start of new content or sections in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -1.23
     تانيه
    -1.18
    tagHelperRunner
    -1.15
     unknownFields
    -1.02
    MLLoader
    -0.98
    FormTagHelper
    -0.95
    ConstraintMaker
    -0.94
    RenderAtEndOf
    -0.91
     @"/
    -0.90
     '\\;'
    -0.90
    POSITIVE LOGITS
    -
    0.48
     
    0.42
    <bos>
    0.38
    postValue
    0.37
     getCategory
    0.37
    ’
    0.36
     fondo
    0.36
    HasBeen
    0.36
    2
    0.36
     duro
    0.35
    Activations Density 1.025%

    No Known Activations