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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 4-GEMMASCOPE-RES-16K
    6. 3465
    Prev
    Next
    INDEX
    Explanations

    patterns of underscores and underscores followed by numbers, indicating variable or function usage in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __':
    
    -0.94
    .*")]
    -0.91
    __":
    
    -0.83
    __':
    -0.80
    <>();
    
    -0.80
     }}$}
    -0.79
    __":
    -0.77
    }));
    
    -0.75
    <>();
    -0.75
     AssemblyTitle
    -0.72
    POSITIVE LOGITS
     ostavi
    0.65
    addContainerGap
    0.48
    faßt
    0.47
    asmuch
    0.46
     daß
    0.45
    _
    0.42
    baan
    0.42
     miest
    0.41
     réessayer
    0.40
    aternion
    0.40
    Activations Density 0.333%

    No Known Activations