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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 23-GEMMASCOPE-RES-16K
    6. 12683
    Prev
    Next
    INDEX
    Explanations

    phrases that inquire about reasons or justifications, particularly involving questions and explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegistryLite
    -0.70
    #+#
    -0.68
    HostException
    -0.65
    URLException
    -0.63
    Do
    -0.62
    Hozzáférés
    -0.62
    Билгалдахарш
    -0.60
    SupportActionBar
    -0.60
    dos
    -0.59
    mog
    -0.59
    POSITIVE LOGITS
     did
    2.29
    did
    1.97
    Did
    1.92
     Did
    1.91
     DID
    1.45
     didn
    1.38
    DID
    1.36
     didnt
    1.35
    didn
    1.21
     DIDN
    1.09
    Activations Density 0.314%

    No Known Activations