© 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 - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 3315
    Prev
    Next
    INDEX
    Explanations

    narratives or phrases that reveal surprising outcomes or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ợ
    -0.61
    illoin
    -0.60
    claimer
    -0.59
    ślę
    -0.56
    ztály
    -0.55
     οπο
    -0.55
    harapkan
    -0.55
    amemnon
    -0.52
    ftagPool
    -0.51
    ilosop
    -0.51
    POSITIVE LOGITS
     ternyata
    0.86
     actually
    0.85
    原来
    0.82
    原來
    0.81
     bleek
    0.76
     مشين
    0.74
     Ternyata
    0.73
     blijkt
    0.72
    actually
    0.71
    Actually
    0.71
    Activations Density 0.380%

    No Known Activations