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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 14320
    Prev
    Next
    INDEX
    Explanations

    the presence of conditional statements in queries or code segments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.65
     MotionEvent
    -0.55
     &___
    -0.52
    '));
    
    -0.52
    protoimpl
    -0.50
     soon
    -0.50
     ill
    -0.50
     Boll
    -0.49
    )++;
    -0.49
    createClass
    -0.49
    POSITIVE LOGITS
    where
    1.47
    WHERE
    1.38
    Where
    1.10
     WHERE
    1.00
     Where
    0.91
    donde
    0.84
    где
    0.82
    wheres
    0.79
    wherein
    0.78
    où
    0.77
    Activations Density 0.158%

    No Known Activations