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. 23-GEMMASCOPE-RES-16K
    6. 12101
    Prev
    Next
    INDEX
    Explanations

    Java package declarations and import statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     RSSSF
    -0.58
    zzleHttp
    -0.51
     abstrato
    -0.49
    |}{$
    -0.49
     appartiennent
    -0.49
    IMPORTED
    -0.48
     åt
    -0.48
     soprav
    -0.48
    ┬
    -0.47
    mybatisplus
    -0.47
    POSITIVE LOGITS
    example
    0.78
     <<<<<<<<<<<<<<
    0.67
    mycompany
    0.66
    PerformLayout
    0.65
    })));
    0.60
    epam
    0.57
    Example
    0.56
    GeneratedCode
    0.56
    shad
    0.56
     سكانية
    0.56
    Activations Density 0.134%

    No Known Activations