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. 6257
    Prev
    Next
    INDEX
    Explanations

    programming concepts and data structure references

    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
     gesteld
    -0.59
    Personendaten
    -0.54
     disambiguazione
    -0.54
     мәкал
    -0.52
    ismet
    -0.52
    vriende
    -0.51
    UVWXYZ
    -0.50
    település
    -0.50
     lecz
    -0.50
     wikipagina
    -0.50
    POSITIVE LOGITS
    onAttach
    0.45
    TokenNameLBRACE
    0.40
     onBind
    0.39
    URLException
    0.38
     anon
    0.37
     haka
    0.36
    IModel
    0.36
    ISU
    0.36
    MMA
    0.36
     пер
    0.36
    Activations Density 2.862%

    No Known Activations