© 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. 13489
    Prev
    Next
    INDEX
    Explanations

    key phrases indicating caution and requirements related to regulations and processes

    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
     MainAxisSize
    -0.59
    ConstraintMaker
    -0.55
    ApiOperation
    -0.55
    contentLoaded
    -0.55
     doInBackground
    -0.55
    sempre
    -0.53
     iNdEx
    -0.53
     élector
    -0.52
    siempre
    -0.52
    styleType
    -0.52
    POSITIVE LOGITS
     failure
    1.48
     Failure
    1.39
    Failure
    1.35
    failure
    1.20
     failing
    1.18
     Failing
    1.07
     FAILURE
    1.06
    Failing
    1.06
     failures
    0.97
    failing
    0.92
    Activations Density 0.423%

    No Known Activations