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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 13424
    Prev
    Next
    INDEX
    Explanations

    numeric values and related data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.66
     
    -0.53
     super
    -0.51
     $
    -0.49
    g
    -0.47
    ?
    -0.44
     B
    -0.44
     g
    -0.43
     \\
    -0.43
     sensitivity
    -0.43
    POSITIVE LOGITS
     bezeichneter
    0.87
    enumii
    0.84
    ).]
    0.79
    enumi
    0.77
    下载附件
    0.77
     ddelweddau
    0.76
    ")));
    
    0.76
    ."</
    0.75
    '):
    
    0.75
    "):
    
    0.75
    Activations Density 0.465%

    No Known Activations