Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 2910
    Prev
    Next
    INDEX
    Explanations

    phrases related to government qualifications and integrity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     therefrom
    -0.76
     thereto
    -0.71
     Incidentally
    -0.69
     Efq
    -0.68
     ſame
    -0.65
     ſa
    -0.65
     faſt
    -0.63
    Zdroj
    -0.63
     régime
    -0.63
     Roskov
    -0.61
    POSITIVE LOGITS
    ustainable
    0.53
    いと
    0.52
    ADVERTISEMENT
    0.50
    цуз
    0.49
     newOwner
    0.47
     Kontext
    0.47
     bArr
    0.47
     napa
    0.47
     attendu
    0.44
     réparer
    0.44
    Activations Density 0.118%

    No Known Activations