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. 10-GEMMASCOPE-RES-16K
    6. 2312
    Prev
    Next
    INDEX
    Explanations

    references to prominent physicists and their theories in the field of condensed matter physics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.78
    toHaveBeenCalled
    -0.69
     itſelf
    -0.64
    TestingModule
    -0.62
    ."],
    -0.62
     AssemblyTitle
    -0.62
    ]='\
    -0.62
    __":
    -0.62
    >",
    
    -0.59
     ""],
    -0.58
    POSITIVE LOGITS
    mybatisplus
    0.56
     병
    0.50
    fors
    0.49
     economico
    0.47
    ώ
    0.46
    hey
    0.45
    ules
    0.44
    Joy
    0.44
    netbeans
    0.44
    Insee
    0.44
    Activations Density 0.592%

    No Known Activations