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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3152
    Prev
    Next
    INDEX
    Explanations

    technical terms related to data manipulation or structures

    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
    klub
    -0.47
     corpi
    -0.47
    setu
    -0.44
    ีน
    -0.44
     použit
    -0.44
    enus
    -0.43
    ruz
    -0.43
     Milne
    -0.43
     cuerpos
    -0.42
    даря
    -0.42
    POSITIVE LOGITS
    KommentareTeilen
    0.81
     للاسماء
    0.70
     Numerade
    0.69
    новниш
    0.67
    Gdx
    0.66
    UnknownFields
    0.66
     disambiguazione
    0.65
    :✨
    0.64
    GEBURTS
    0.63
     jadx
    0.63
    Activations Density 0.207%

    No Known Activations