© 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. 2-GEMMASCOPE-RES-16K
    6. 8702
    Prev
    Next
    INDEX
    Explanations

    terms related to film production and award recognition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.77
     متعلقه
    -0.68
    +#+#
    -0.65
    mybatisplus
    -0.62
     vicenda
    -0.60
    MENAFN
    -0.59
    VIAF
    -0.59
     insuffisamment
    -0.59
     INTERESAR
    -0.58
    lamento
    -0.57
    POSITIVE LOGITS
     coached
    0.63
     quarterback
    0.62
     captains
    0.59
     authors
    0.57
     pilo
    0.57
     coach
    0.56
     Regie
    0.56
     photographer
    0.55
     Authors
    0.54
    irmanship
    0.53
    Activations Density 0.442%

    No Known Activations