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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6-GEMMASCOPE-RES-16K
    6. 352
    Prev
    Next
    INDEX
    Explanations

    references to authors in scientific publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __':
    
    -1.03
    uxxxx
    -0.98
    Portail
    -0.86
    __":
    
    -0.82
     MainAxisSize
    -0.80
    StructEnd
    -0.79
    AutoresizingMask
    -0.77
     myſelf
    -0.77
    NOPQRST
    -0.74
    */].
    -0.71
    POSITIVE LOGITS
    et
    0.79
     et
    0.76
    ET
    0.59
    Erreferentziak
    0.57
    al
    0.46
    er
    0.46
    y
    0.45
    Et
    0.45
    id
    0.44
    
    0.43
    Activations Density 0.052%

    No Known Activations