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. 7553
    Prev
    Next
    INDEX
    Explanations

    topics related to coding and technical specifications, particularly in programming and software development

    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
     HasFactory
    -0.68
     Seeder
    -0.61
     Affiliations
    -0.61
     raça
    -0.61
    coaster
    -0.60
    ptor
    -0.58
    principalColumn
    -0.57
    Autoritní
    -0.56
    UniformLocation
    -0.56
    kháu
    -0.56
    POSITIVE LOGITS
     footage
    0.65
    躇
    0.61
    rapnel
    0.60
     stuff
    0.57
    stuff
    0.55
     pieces
    0.54
     junk
    0.53
     evidence
    0.52
    RenderAtEndOf
    0.51
    adone
    0.50
    Activations Density 1.562%

    No Known Activations