© 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. 5112
    Prev
    Next
    INDEX
    Explanations

    references to body parts, especially those related to the head and face

    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
     CreateTagHelper
    -0.78
     ſmall
    -0.74
    contentLoaded
    -0.71
     Majefty
    -0.70
     useRouter
    -0.70
     cref
    -0.69
    InjectAttribute
    -0.69
    Παραπομπές
    -0.68
    Personendaten
    -0.67
     Jehová
    -0.64
    POSITIVE LOGITS
    Története
    0.54
    AddTagHelper
    0.52
    execSQL
    0.52
    setopt
    0.49
    satunya
    0.47
     uuidv
    0.46
    țional
    0.46
     ModelRenderer
    0.46
    pubmed
    0.46
     Chwiliwch
    0.45
    Activations Density 0.212%

    No Known Activations