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

    Neuronpedia

    APICircuit 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. 12-GEMMASCOPE-RES-16K
    6. 2971
    Prev
    Next
    INDEX
    Explanations

    metadata and structure elements related to data processing and server communication protocols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Spots technical references to input(s) or input-related fields in code and documentation.

    oai_token-act-pair · gpt-5-miniTriggered by @phamvanluong2003
    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
     Oggi
    -0.52
     newBuilder
    -0.49
    ACHI
    -0.48
    UNTIME
    -0.47
    apos
    -0.47
    
    -0.46
    RectangleBorder
    -0.45
    iciado
    -0.45
    toJSONString
    -0.45
     awakeFromNib
    -0.44
    POSITIVE LOGITS
     елның
    0.74
    BeginContext
    0.70
    fromnode
    0.69
    Geplaatst
    0.66
    twimg
    0.65
    CodedInputStream
    0.64
    ReusableCell
    0.63
     iprot
    0.63
    HttpPut
    0.62
    DatabaseError
    0.61
    Activations Density 1.295%

    No Known Activations