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

    Neuronpedia

    APICircuit 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. 14405
    Prev
    Next
    INDEX
    Explanations

    elements related to performance and evaluations in various contexts

    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
    ChildScrollView
    -0.66
     queſta
    -0.61
    IsMutable
    -0.61
    XmlAccessorType
    -0.61
     <<<<<<<<<<<<<<
    -0.60
    addContainerGap
    -0.60
    WriteLiteral
    -0.60
    ConstraintMaker
    -0.60
    RegressionTest
    -0.59
    pantalones
    -0.58
    POSITIVE LOGITS
     its
    0.34
     nõ
    0.33
     asiático
    0.33
     Moscú
    0.32
    Its
    0.31
     nito
    0.31
     magnétique
    0.31
    förs
    0.31
     delà
    0.30
    løs
    0.29
    Activations Density 0.977%

    No Known Activations