© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 794
    Prev
    Next
    INDEX
    Explanations

    references to various applications and properties of substances or devices

    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
     propOrder
    -0.36
    RTDA
    -0.33
     nemen
    -0.32
    RTLR
    -0.31
     mess
    -0.30
    vertra
    -0.30
    PARATUS
    -0.30
    Personendaten
    -0.29
    PDATE
    -0.29
    [*]
    -0.28
    POSITIVE LOGITS
    用途
    1.83
     purposes
    1.64
     purpose
    1.51
     usos
    1.45
     usefulness
    1.45
     usage
    1.45
     Purposes
    1.41
    purposes
    1.41
    purpose
    1.39
    Purpose
    1.34
    Activations Density 0.802%

    No Known Activations