© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 2825
    Prev
    Next
    INDEX
    Explanations

    references to problems and questions that indicate challenges or issues in various contexts

    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
     EconPapers
    -1.12
     OFDb
    -1.08
    addCriterion
    -0.93
    principalColumn
    -0.92
    URLException
    -0.87
    enumii
    -0.86
    ."));
    -0.79
    )"),
    -0.79
    ]--;
    -0.79
     myſelf
    -0.79
    POSITIVE LOGITS
     here
    1.07
     is
    0.75
     hierbei
    0.69
     for
    0.63
     εδώ
    0.62
     aquí
    0.61
    :
    0.60
     acá
    0.59
     aici
    0.58
     dabei
    0.58
    Activations Density 0.250%

    No Known Activations