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. 14931
    Prev
    Next
    INDEX
    Explanations

    narratives about personal growth and life experiences

    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
    发表于
    -0.48
    おめでとうございます
    -0.46
    umably
    -0.44
     sikkert
    -0.43
    rungsseite
    -0.40
     themselves
    -0.40
     dé
    -0.39
     boste
    -0.38
    њи
    -0.38
     mohou
    -0.38
    POSITIVE LOGITS
    #+#
    0.59
    UnusedPrivate
    0.48
     my
    0.47
    stupid
    0.46
     AttributeSet
    0.45
     mojej
    0.43
    Попис
    0.43
     Biôgrafia
    0.42
    huber
    0.42
     stupidly
    0.42
    Activations Density 0.683%

    No Known Activations