Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 9563
    Prev
    Next
    INDEX
    Explanations

    references to the state and federal government or funding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.75
    +#+#
    -0.62
    Bibliograf
    -0.61
     متعلقه
    -0.59
     tartalomajánló
    -0.59
     INVENTION
    -0.58
     Wiktionnaire
    -0.57
    сылкі
    -0.55
    tagHelperRunner
    -0.55
    ագրություններ
    -0.53
    POSITIVE LOGITS
     state
    4.34
    state
    3.62
     STATE
    2.70
     states
    2.69
    STATE
    2.62
     estado
    2.60
     State
    2.56
    State
    2.52
     état
    2.27
     estatales
    2.22
    Activations Density 0.140%

    No Known Activations