© 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. 14-GEMMASCOPE-RES-16K
    6. 5593
    Prev
    Next
    INDEX
    Explanations

    media citations or mentions of sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Identyfik
    -0.71
    InputTagHelper
    -0.70
    )++;
    -0.59
    السكان
    -0.52
    arResult
    -0.52
    曖昧さ回避
    -0.50
    transQ
    -0.49
    onets
    -0.48
    ktop
    -0.48
    Stateless
    -0.47
    POSITIVE LOGITS
     '\\;'
    0.73
    SizeF
    0.59
     reported
    0.59
     according
    0.58
     quoted
    0.58
    quoted
    0.56
    according
    0.54
     Reported
    0.51
     ifølge
    0.51
    reported
    0.51
    Activations Density 0.139%

    No Known Activations