© 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. 14-GEMMASCOPE-RES-16K
    6. 9104
    Prev
    Next
    INDEX
    Explanations

    terms related to processes, evaluations, and discussions in qualitative research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AttributeSet
    -0.74
    
    -0.70
     MainAxisSize
    -0.68
     onCreateView
    -0.67
     насељу
    -0.65
    AttributeSet
    -0.63
    ByDefault
    -0.62
    <?
    -0.60
     AssemblyVersion
    -0.58
     MotionEvent
    -0.57
    POSITIVE LOGITS
     until
    0.81
    直到
    0.66
    until
    0.66
     ensure
    0.64
    直至
    0.62
     ensuring
    0.61
    Until
    0.59
     ensured
    0.58
     puas
    0.58
     UNTIL
    0.57
    Activations Density 0.289%

    No Known Activations