© 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. 14-GEMMASCOPE-RES-16K
    6. 13186
    Prev
    Next
    INDEX
    Explanations

    references to organizational structures or legal terms related to companies

    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
    
    -0.71
    EnableWeb
    -0.61
    раздо
    -0.58
    setopt
    -0.56
     !_
    -0.52
    tagHelperRunner
    -0.51
    estacks
    -0.51
     realises
    -0.50
    LookAnd
    -0.49
     Abp
    -0.48
    POSITIVE LOGITS
     كومونز
    0.63
    spaceBetween
    0.56
     ejus
    0.54
    AutoScale
    0.53
    cshtml
    0.49
     obce
    0.48
    oredCriteria
    0.47
     ultime
    0.47
    GEBURTSDATUM
    0.47
     tibi
    0.47
    Activations Density 0.219%

    No Known Activations