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. 17-GEMMASCOPE-RES-16K
    6. 5765
    Prev
    Next
    INDEX
    Explanations

    information related to measurements or data analysis

    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
     animado
    -0.63
     officielle
    -0.62
     amnesty
    -0.62
     encephalitis
    -0.60
     obrigado
    -0.60
     equinox
    -0.59
     flocc
    -0.58
     intéress
    -0.58
     Propaganda
    -0.58
     bocca
    -0.58
    POSITIVE LOGITS
    ########.
    0.66
    HasForeignKey
    0.66
     AssemblyCulture
    0.62
    ');?>
    0.62
    transQ
    0.60
    +");
    0.60
    AnchorTagHelper
    0.58
    ')";
    0.57
    )")
    0.57
    writeFieldEnd
    0.57
    Activations Density 0.453%

    No Known Activations