© 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. 2-GEMMASCOPE-RES-16K
    6. 8141
    Prev
    Next
    INDEX
    Explanations

    quotation marks or punctuation typically used for dialogue or direct quotes

    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
     HasFactory
    -0.73
     disambiguazione
    -0.70
    Gambas
    -0.63
    déric
    -0.60
    iastes
    -0.59
     препратки
    -0.58
     StringTokenizer
    -0.58
    mphony
    -0.57
     дописавши
    -0.57
    حوالہ
    -0.57
    POSITIVE LOGITS
    <eos>
    0.58
     groene
    0.58
    principalTable
    0.55
    yntaxException
    0.54
    )))));
    0.53
    >{@
    0.53
    iecie
    0.52
    //</
    0.52
    ))));
    0.52
     coté
    0.51
    Activations Density 0.108%

    No Known Activations