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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6748
    Prev
    Next
    INDEX
    Explanations

    references to intent or actions involving searching, wanting, or discovering something

    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
    Datuak
    -0.84
    AutoScaleMode
    -0.75
     Vikipedi
    -0.75
    rungsseite
    -0.71
    abestanden
    -0.69
     utafitiHapana
    -0.68
     OMITBAD
    -0.68
     protoimpl
    -0.66
     يتيمه
    -0.65
     defStyleAttr
    -0.63
    POSITIVE LOGITS
     scurt
    0.54
    ufficio
    0.53
    ADELPHIA
    0.50
     vectorielles
    0.49
     setempat
    0.48
     etkili
    0.47
     calitate
    0.47
     ModelExpression
    0.47
     geométrico
    0.46
     vectorielle
    0.46
    Activations Density 0.149%

    No Known Activations