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. 23-GEMMASCOPE-RES-16K
    6. 12389
    Prev
    Next
    INDEX
    Explanations

    terms related to conditions or actions involving 'pre', 'ver', and associated prefixes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.47
    tralight
    -0.47
     Biôgrafia
    -0.45
    appliquer
    -0.45
    impan
    -0.44
    HasForeignKey
    -0.44
    isuus
    -0.44
    epiece
    -0.44
    lane
    -0.43
    पया
    -0.43
    POSITIVE LOGITS
     صوتيه
    0.63
    bootstrapcdn
    0.61
    stateProvider
    0.61
     Efq
    0.59
    Spoljašnje
    0.56
     againſt
    0.56
     houſe
    0.56
     Monfieur
    0.55
    MLLoader
    0.55
     Houſe
    0.54
    Activations Density 0.099%

    No Known Activations