Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 6363
    Prev
    Next
    INDEX
    Explanations

    keywords related to API and empowerment in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "}},
    -0.59
    krat
    -0.58
    aluz
    -0.57
    CRIP
    -0.55
    {`
    -0.55
    addPreferredGap
    -0.54
    ownic
    -0.53
    Moj
    -0.52
     Stif
    -0.52
    ENTY
    -0.52
    POSITIVE LOGITS
     noires
    0.80
     يتيمه
    0.75
     है
    0.72
    SourceChecksum
    0.72
     vertes
    0.72
    Beschrijving
    0.70
     médicas
    0.68
     veneta
    0.67
    ApiModelProperty
    0.66
     artesanales
    0.65
    Activations Density 0.024%

    No Known Activations