© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 644
    Prev
    Next
    INDEX
    Explanations

    references to object properties and methods in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     faſt
    -0.69
     ſta
    -0.56
     ſch
    -0.56
    )</
    -0.56
     ſind
    -0.56
     незавершена
    -0.56
     }</
    -0.55
     ſtand
    -0.54
     للمعارف
    -0.54
     pleaſure
    -0.54
    POSITIVE LOGITS
     =
    0.56
     +=
    0.50
     ayrıca
    0.46
     &=
    0.43
     inoltre
    0.42
     infatti
    0.40
    +="
    0.40
     |=
    0.40
     voilà
    0.39
     .=
    0.39
    Activations Density 0.326%

    No Known Activations