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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 12804
    Prev
    Next
    INDEX
    Explanations

    functions and methods related to saving data and performing operations on it

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

    Actions of saving, uploading, sending, downloading, or loading

    np_acts-logits-general · gemini-2.0-flash

    save, upload, send, download, load, copy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArgsConstructor
    -0.76
    VersionUID
    -0.55
     Audiodateien
    -0.53
    DrawerToggle
    -0.49
     LoggerFactory
    -0.47
     jadx
    -0.46
    melidir
    -0.43
    sprodu
    -0.43
    SerializedName
    -0.43
     صوتيه
    -0.43
    POSITIVE LOGITS
    all
    0.75
     oneself
    0.74
    Yourself
    0.74
    Entire
    0.73
     entire
    0.72
     Theſe
    0.71
    单个
    0.70
     ulang
    0.70
     all
    0.69
    Existing
    0.69
    Activations Density 0.407%

    No Known Activations