Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 4195
    Prev
    Next
    INDEX
    Explanations

    references to actions and interactions involving groups of people or entities

    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
     offer
    -0.39
    PERS
    -0.38
    Lähteet
    -0.37
     Sentinel
    -0.37
     offrire
    -0.36
    avid
    -0.35
     anahtar
    -0.35
    igo
    -0.35
     Chronicles
    -0.34
     Vereins
    -0.34
    POSITIVE LOGITS
    IntoConstraints
    0.83
    NameInMap
    0.79
    XMLSchema
    0.78
     صوتيه
    0.73
     saites
    0.71
    TemporalType
    0.68
     hears
    0.65
    IsMutable
    0.64
     autorytatywna
    0.64
    TestingModule
    0.64
    Activations Density 0.310%

    No Known Activations