© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 28274
    Prev
    Next
    INDEX
    Explanations

    terms related to organizations and departments involved in crime and security

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    names of organizations or services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EClass
    -0.57
    baidu
    -0.49
     StyleSheet
    -0.48
    thebibliography
    -0.47
    ScopeManager
    -0.46
     tonight
    -0.44
     today
    -0.44
    🎰
    -0.44
    kswagen
    -0.44
    <eos>
    -0.43
    POSITIVE LOGITS
    </h3>
    0.80
    </h4>
    0.77
    </h2>
    0.77
     betweenstory
    0.67
     }}$}
    0.65
    ########.
    0.65
    })$}
    0.64
    </strong>
    0.63
    </h5>
    0.63
    ')))
    0.63
    Activations Density 0.040%

    No Known Activations