© 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. 12852
    Prev
    Next
    INDEX
    Explanations

    phrases that signal opposition or resistance to a topic

    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
    nemo
    -0.68
    ERTY
    -0.65
    jména
    -0.65
    談社
    -0.65
    élien
    -0.64
    Txn
    -0.63
     собі
    -0.60
    󠁿
    -0.60
    UMBIA
    -0.59
     Gem
    -0.59
    POSITIVE LOGITS
    Against
    2.63
     Against
    2.63
     against
    2.62
    against
    2.47
     AGAINST
    2.38
     gegen
    1.82
     contre
    1.66
     tegen
    1.63
     melawan
    1.47
     против
    1.46
    Activations Density 0.092%

    No Known Activations