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

    Neuronpedia

    APICircuit 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. 25-GEMMASCOPE-RES-16K
    6. 5674
    Prev
    Next
    INDEX
    Explanations

    references to lists or collections of items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    이는
    -0.56
     समीक्षाएं
    -0.54
    家は
    -0.51
    atero
    -0.49
    BASEPATH
    -0.49
     uParam
    -0.48
     who
    -0.48
     대한
    -0.47
    #+#
    -0.46
    ophilia
    -0.45
    POSITIVE LOGITS
     में
    1.04
    에서
    1.03
    where
    0.98
     where
    0.97
     میں
    0.95
    Where
    0.90
    中
    0.90
    లో
    0.87
     où
    0.86
     Where
    0.85
    Activations Density 0.077%

    No Known Activations