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. 4170
    Prev
    Next
    INDEX
    Explanations

    references to academic degrees and terms related to academic qualifications, particularly in the field of physics and its sub-disciplines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     STC
    -0.76
    EndContext
    -0.76
    <tr>
    -0.74
    ostok
    -0.67
    JAKARTA
    -0.66
    writerow
    -0.64
    kháu
    -0.63
    DataURL
    -0.63
    存于互联网档案馆
    -0.63
    ונ
    -0.63
    POSITIVE LOGITS
     Ph
    1.39
     Phillies
    1.38
    Ph
    1.34
     PH
    1.26
     Philo
    1.25
    PH
    1.22
     ph
    1.20
     Φ
    1.19
     Phillips
    1.16
     phthal
    1.14
    Activations Density 0.277%

    No Known Activations