Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 2263
    Prev
    Next
    INDEX
    Explanations

    terms related to the processes and systems of waste treatment and settling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    following "a" or "of"

    np_acts-logits-general · gemini-2.0-flash

    anaerobic bacterium treatment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FetchType
    -0.70
     "..\..\
    -0.69
    TintMode
    -0.65
    //
    -0.62
    TypedDataSet
    -0.62
    EndGlobalSection
    -0.58
    astéroïdes
    -0.57
     فريبيس
    -0.57
    EndContext
    -0.56
    principalColumn
    -0.56
    POSITIVE LOGITS
     treatment
    1.02
     Treatment
    0.94
     treat
    0.87
    treatment
    0.86
    Treatment
    0.84
     Treat
    0.82
     treating
    0.82
     treated
    0.81
     TREATMENT
    0.80
    treat
    0.79
    Activations Density 0.247%

    No Known Activations