© 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. 4-GEMMASCOPE-RES-16K
    6. 1809
    Prev
    Next
    INDEX
    Explanations

    references to being at home or related concepts of isolation and exclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    处于
    -0.44
    ']")
    -0.43
     current
    -0.42
     folgendes
    -0.41
    cc
    -0.41
     valid
    -0.39
    ten
    -0.39
    ỏa
    -0.38
    te
    -0.37
     following
    -0.37
    POSITIVE LOGITS
     AssemblyCulture
    1.31
     للمعارف
    1.10
     تضيفلها
    1.04
    SequentialGroup
    1.01
    ंदीखरीदारी
    1.00
    URLException
    0.99
     Administrativna
    0.95
    tagHelperRunner
    0.94
    новниш
    0.93
    Datuak
    0.92
    Activations Density 0.318%

    No Known Activations