© 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. 1944
    Prev
    Next
    INDEX
    Explanations

    specific types of utensils and their usage in dining contexts

    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
    aktery
    -0.51
    цен
    -0.49
    Competing
    -0.47
    Hochspringen
    -0.46
    GrantedAuthority
    -0.45
    dut
    -0.45
    ις
    -0.45
     honour
    -0.44
    惮
    -0.44
     walls
    -0.43
    POSITIVE LOGITS
    ########.
    0.99
     насељу
    0.76
     estekak
    0.68
    Становништво
    0.68
    ViewFeatures
    0.63
    GEBURTSDATUM
    0.61
    webElement
    0.60
     Италијани
    0.60
    UnsafeEnabled
    0.58
    +#+#
    0.56
    Activations Density 2.900%

    No Known Activations