© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 354
    Prev
    Next
    INDEX
    Explanations

    terms related to registration and registries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cgi
    -0.66
    bhan
    -0.65
     lom
    -0.64
    Mith
    -0.64
    SCAPE
    -0.62
    Lom
    -0.62
    aspectj
    -0.60
     VPN
    -0.60
     المثال
    -0.59
     Jonson
    -0.59
    POSITIVE LOGITS
     registered
    2.43
     REGISTER
    2.26
     register
    2.24
     Register
    2.20
     registers
    2.20
     Regist
    2.15
     registrations
    2.15
     registration
    2.14
    registered
    2.14
     Registered
    2.09
    Activations Density 0.046%

    No Known Activations