© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 3680
    Prev
    Next
    INDEX
    Explanations

    technical terms and symbols used in programming or mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.72
     ujednoznacz
    -0.67
    ViewFeatures
    -0.60
    hdysval
    -0.53
     Winfield
    -0.51
    Obrázky
    -0.51
    GrantedAuthority
    -0.50
    LinkId
    -0.49
    PhysRevD
    -0.49
     للمعارف
    -0.49
    POSITIVE LOGITS
     mod
    1.37
    mod
    1.28
     modulo
    1.27
     Mod
    1.20
    bmod
    1.16
     MOD
    1.16
    Mod
    1.16
    MOD
    1.13
     modulus
    1.11
     %
    1.10
    Activations Density 0.667%

    No Known Activations