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. 1-GEMMASCOPE-RES-16K
    6. 8427
    Prev
    Next
    INDEX
    Explanations

    requests for help or assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -0.62
    󠁿
    -0.59
     Wikiseite
    -0.59
     endforeach
    -0.59
     nakalista
    -0.57
    ukunft
    -0.55
     препратки
    -0.55
     anún
    -0.54
     kautta
    -0.53
    autaire
    -0.52
    POSITIVE LOGITS
    이
    0.47
    ±
    0.46
     Even
    0.45
    Even
    0.44
     please
    0.44
    .)
    0.43
     ±
    0.43
     pm
    0.41
     na
    0.40
     ceilings
    0.39
    Activations Density 0.299%

    No Known Activations