© 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. 17-GEMMASCOPE-RES-16K
    11. 892
    Prev
    Next
    INDEX
    Explanations

    statements about the validity or status of various claims or beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    saraba
    -0.54
    NameInMap
    -0.54
    Personensuche
    -0.53
    AutoField
    -0.50
    ]();
    -0.47
     intptr
    -0.47
    jspx
    -0.47
     Photocase
    -0.47
     poffe
    -0.45
    НТ
    -0.45
    POSITIVE LOGITS
    EndTag
    0.66
    __":
    0.61
     twofold
    0.60
    =$?
    0.60
     onCreateView
    0.59
    telar
    0.57
     bahwa
    0.56
     kwamba
    0.56
    __':
    0.55
    ellees
    0.55
    Activations Density 0.428%

    No Known Activations