© 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. 16-GEMMASCOPE-RES-16K
    6. 4625
    Prev
    Next
    INDEX
    Explanations

    legal references and court case details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Legal and mathematical references

    np_acts-logits-general · gemini-2.0-flash

    US states and Canadian provinces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 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
    reactstrap
    -0.78
    labus
    -0.72
    didSet
    -0.62
    PhysRevLett
    -0.62
    AddTagHelper
    -0.62
    cticut
    -0.60
    tagHelperRunner
    -0.59
    ectady
    -0.58
    ėse
    -0.57
    INCREF
    -0.57
    POSITIVE LOGITS
     Nebraska
    0.62
     ويكيميديا
    0.59
     Saskatoon
    0.58
    Nebraska
    0.57
    Sask
    0.57
     Saskatchewan
    0.56
    Dakota
    0.56
     Iowa
    0.55
     Sioux
    0.54
    TAWA
    0.53
    Activations Density 0.335%

    No Known Activations