© 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. 5-GEMMASCOPE-RES-16K
    6. 3616
    Prev
    Next
    INDEX
    Explanations

    phrases suggesting alternatives or options for problem-solving

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.80
     ExecuteAsync
    -0.69
     Roskov
    -0.68
    setVerticalGroup
    -0.65
    hyrchwyd
    -0.63
    antMatchers
    -0.62
    EndGlobalSection
    -0.61
    AutoField
    -0.58
    ]")]
    -0.58
    )))));
    -0.58
    POSITIVE LOGITS
     saja
    0.72
     instead
    0.64
     yourself
    0.63
     rather
    0.61
    Rather
    0.61
     plutôt
    0.58
     Instead
    0.56
    Instead
    0.56
     istället
    0.56
     Rather
    0.56
    Activations Density 0.657%

    No Known Activations