© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 8070
    Prev
    Next
    INDEX
    Explanations

    keywords related to data structures and their manipulations in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by "TF" or related to tests/skills

    np_acts-logits-general · gemini-2.0-flash

    API requests and data processing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </b>
    -0.41
    greSQL
    -0.40
     conveniente
    -0.40
     WRITER
    -0.39
    电视台
    -0.38
     commerciaux
    -0.38
    denly
    -0.38
    adget
    -0.38
    hdmi
    -0.38
    ترنت
    -0.38
    POSITIVE LOGITS
     pleaſure
    1.07
    ſelves
    1.05
     ſche
    1.05
     Majefty
    1.04
     ſtate
    1.01
     ſever
    1.01
     houſe
    0.99
     Diſ
    0.98
     Reſ
    0.96
     Jefus
    0.96
    Activations Density 1.120%

    No Known Activations