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. 11825
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conditions or contexts that influence outcomes

    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
    URLException
    -0.66
    väg
    -0.63
     plufieurs
    -0.61
     ainfi
    -0.56
     itſelf
    -0.56
    mace
    -0.53
     fileSize
    -0.51
    batore
    -0.51
    ritsar
    -0.49
    istad
    -0.49
    POSITIVE LOGITS
     under
    1.38
     Under
    1.30
    Under
    1.27
    under
    1.23
     UNDER
    1.18
    UNDER
    1.06
     unter
    0.91
     Sous
    0.83
     underneath
    0.82
     beneath
    0.81
    Activations Density 0.195%

    No Known Activations