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. 2098
    Prev
    Next
    INDEX
    Explanations

    structures and keywords associated with data types and programming functions

    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
     disambiguazione
    -0.60
     varandra
    -0.50
    HasBeenSet
    -0.46
    AccessorTable
    -0.45
    ftagPool
    -0.42
    fromnode
    -0.41
     للاسماء
    -0.40
    tvguidetime
    -0.40
    abstractmethod
    -0.39
     poveznice
    -0.38
    POSITIVE LOGITS
     useful
    0.46
     kard
    0.46
     unstable
    0.44
     excur
    0.44
    ChildScrollView
    0.43
    aarrggbb
    0.42
    ymbol
    0.42
    AISSEE
    0.42
     nack
    0.42
     similar
    0.42
    Activations Density 0.938%

    No Known Activations