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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 12125
    Prev
    Next
    INDEX
    Explanations

    mentions of programs and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    white
    -0.45
     Bélgica
    -0.45
     Melhor
    -0.45
    wet
    -0.43
    isDead
    -0.41
     detecta
    -0.40
     Vieux
    -0.39
    Santé
    -0.39
     tactile
    -0.39
    wild
    -0.38
    POSITIVE LOGITS
     Program
    1.22
     program
    1.16
    Program
    1.13
     PROGRAM
    1.10
     Programs
    1.09
    PROGRAM
    1.08
    Programs
    1.05
     Programme
    1.01
    sprogramm
    0.99
     programs
    0.99
    Activations Density 0.075%

    No Known Activations