© 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. 5955
    Prev
    Next
    INDEX
    Explanations

    multisyllabic words and phrases often related to names or proper nouns

    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
    one
    -0.51
    ONE
    -0.50
    drücken
    -0.50
    êmios
    -0.48
    ulipas
    -0.48
    adaptiveStyles
    -0.48
    mässig
    -0.48
    uffer
    -0.47
    cbb
    -0.47
     Massa
    -0.46
    POSITIVE LOGITS
     varandra
    0.60
    AndEndTag
    0.58
     vPvB
    0.58
     venezolano
    0.57
     peruano
    0.55
    ऋ
    0.53
    tagext
    0.53
    Espèce
    0.51
     ordf
    0.51
     Universitaria
    0.49
    Activations Density 3.061%

    No Known Activations