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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 11592
    Prev
    Next
    INDEX
    Explanations

    functions and commands related to flushing data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AppModule
    -0.85
    +:+
    -0.79
     Roskov
    -0.79
    تقاوى
    -0.78
     FormsModule
    -0.76
     Normdatei
    -0.76
    tvguidetime
    -0.76
    makeConstraints
    -0.75
     AssemblyCulture
    -0.74
    ieteur
    -0.74
    POSITIVE LOGITS
     flip
    1.23
     Flip
    1.01
    flip
    0.98
     Fli
    0.97
    fl
    0.96
    FLUSH
    0.96
    Fl
    0.96
     fl
    0.95
    Flick
    0.94
    Flip
    0.94
    Activations Density 0.148%

    No Known Activations