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. 3454
    Prev
    Next
    INDEX
    Explanations

    programming-related class names and types

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

    Class/Object/Type definition

    np_acts-logits-general · gemini-2.0-flash

    class inheritance or definition

    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
    ].
    -0.79
    .),
    -0.76
    ).
    -0.76
    ),
    -0.73
    .);
    -0.73
    .).
    -0.73
    ],
    -0.69
    .");
    -0.69
    .)
    -0.69
    ?).
    -0.69
    POSITIVE LOGITS
     extends
    1.40
     {
    
    0.89
     implements
    0.89
    setVerticalGroup
    0.79
     inherits
    0.75
     дописавши
    0.74
    extends
    0.73
     {
    
    
    0.73
     Normdatei
    0.73
     للاسماء
    0.73
    Activations Density 0.105%

    No Known Activations