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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10557
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "some" and its variations, indicating a focus on quantified or unspecified quantities

    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
    󠁢
    -0.34
    RTLU
    -0.31
    の一つ
    -0.30
     any
    -0.30
    </tr>
    -0.30
    se
    -0.29
     alguno
    -0.29
     poffe
    -0.29
     будь
    -0.29
     något
    -0.29
    POSITIVE LOGITS
     sort
    0.84
    things
    0.83
     semblance
    0.77
     wenige
    0.69
    ones
    0.69
     متعلقه
    0.66
     pretty
    0.63
     nice
    0.63
     AssemblyTitle
    0.62
    thig
    0.62
    Activations Density 0.177%

    No Known Activations