© 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-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 4847
    Prev
    Next
    INDEX
    Explanations

    references to "Nasir" or related names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    าศ
    -0.30
     κατα
    -0.28
    มือ
    -0.27
     quieras
    -0.26
    guantes
    -0.26
     regola
    -0.26
     hermanas
    -0.26
     bevor
    -0.26
     close
    -0.25
     коммуна
    -0.25
    POSITIVE LOGITS
    帖最后由
    0.82
    httphttps
    0.75
     препратки
    0.73
    دانشنامهٔ
    0.66
    IsMutable
    0.65
    findpost
    0.64
    featureID
    0.63
    fjspx
    0.61
    %)$
    0.60
     beginnetje
    0.60
    Activations Density 0.341%

    No Known Activations