© 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. 2-GEMMASCOPE-RES-16K
    6. 8531
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the word "against."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    élien
    -0.60
     Gem
    -0.59
    ERTY
    -0.58
    קישורים
    -0.58
    談社
    -0.58
     GEM
    -0.58
    atimes
    -0.56
    jména
    -0.55
    ạp
    -0.54
    fres
    -0.52
    POSITIVE LOGITS
     against
    3.98
     Against
    3.74
    Against
    3.67
    against
    3.64
     AGAINST
    3.34
     gegen
    2.55
     contre
    2.52
     tegen
    2.27
     против
    2.14
     melawan
    2.11
    Activations Density 0.058%

    No Known Activations