© 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. 25-GEMMASCOPE-RES-16K
    6. 788
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to legal procedures and agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     DialogResult
    -0.71
    tagext
    -0.66
    lacian
    -0.63
    NameInMap
    -0.59
     leveraging
    -0.54
     ihop
    -0.54
    rillas
    -0.54
    互联网档案馆
    -0.54
     capturing
    -0.54
     address
    -0.54
    POSITIVE LOGITS
    got
    0.50
    '}),
    0.49
    ✭✭
    0.49
    UserScript
    0.49
    gono
    0.47
    ButtonStyle
    0.47
    URLException
    0.47
    anthin
    0.47
    gunakan
    0.47
    lgari
    0.46
    Activations Density 0.716%

    No Known Activations