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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 14138
    Prev
    Next
    INDEX
    Explanations

    phrases related to advertising or affiliate marketing content

    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
     IBRARY
    -0.74
    󠁬
    -0.73
    حياته
    -0.69
    MENAFN
    -0.67
     dieſen
    -0.66
     RSITY
    -0.65
     kapture
    -0.65
    VERTISEMENT
    -0.65
     メンテナ
    -0.64
    ſicht
    -0.64
    POSITIVE LOGITS
     принци
    0.27
    Reader
    0.25
     kadar
    0.24
     reader
    0.24
     erscheint
    0.24
     matière
    0.23
     Боль
    0.23
     нес
    0.23
     readers
    0.23
     scan
    0.22
    Activations Density 0.108%

    No Known Activations