© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 5158
    Prev
    Next
    INDEX
    Explanations

    specific terms related to governance and oversight issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -0.59
    0
    -0.58
    3
    -0.58
     on
    -0.53
    5
    -0.53
    2
    -0.53
    ?
    -0.51
     of
    -0.51
    8
    -0.51
    ↵↵
    -0.50
    POSITIVE LOGITS
     كومونز
    1.04
     ddelweddau
    0.98
    }{*}{
    0.93
    ghijklmnop
    0.93
    ]")]
    0.92
    YourGuide
    0.92
    GHIJKLM
    0.91
    éphane
    0.90
     }}$}
    0.90
    ']))
    
    0.89
    Activations Density 1.300%

    No Known Activations