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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 145
    Prev
    Next
    INDEX
    Explanations

    phrases related to professional roles and transitions in the culinary field

    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
     matéria
    -0.29
    .
    -0.27
     (
    -0.26
     *
    -0.25
    '
    -0.24
    <eos>
    -0.24
     Entscheid
    -0.24
     chuva
    -0.24
     fake
    -0.23
     con
    -0.23
    POSITIVE LOGITS
    DockStyle
    0.94
    sizeCache
    0.91
     '\\;'
    0.91
    ########.
    0.91
    fillType
    0.89
     queſta
    0.88
     يتيمه
    0.87
     ſind
    0.85
     насељу
    0.84
    twimg
    0.84
    Activations Density 0.448%

    No Known Activations