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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 5044
    Prev
    Next
    INDEX
    Explanations

    complex legal terminology and claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.68
     …
    -0.62
    TestingModule
    -0.52
     PyTuple
    -0.52
     ...
    -0.51
    "
    -0.51
     
    -0.50
     createState
    -0.47
     (
    -0.46
    /
    -0.44
    POSITIVE LOGITS
    GraphicsUnit
    0.82
    #+#
    0.81
     myſelf
    0.81
    Clik
    0.78
    /*
    0.77
     kasarigan
    0.76
    })*/
    0.74
     $_(
    0.74
     iſt
    0.73
    });*/
    0.73
    Activations Density 0.048%

    No Known Activations