© 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. 1257
    Prev
    Next
    INDEX
    Explanations

    negative integers or references to negative values

    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
    -0.75
    ContextHolder
    -0.65
    th
    -0.64
    TagHelper
    -0.62
     NgModule
    -0.59
    MockBean
    -0.55
     <<<<<<<<<<<<<<
    -0.54
    LEncoder
    -0.52
     Référence
    -0.52
    argout
    -0.52
    POSITIVE LOGITS
    year
    0.68
    ounce
    0.62
    hecta
    0.60
    carat
    0.59
    foot
    0.58
    kilometer
    0.58
    acre
    0.57
    minute
    0.56
     to
    0.55
    YEAR
    0.55
    Activations Density 0.290%

    No Known Activations