© 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. 3699
    Prev
    Next
    INDEX
    Explanations

    phrases related to guidelines, rules, or regulations

    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
     altrett
    -0.53
     GIPHY
    -0.51
    ioutil
    -0.49
    дото
    -0.49
    >{"
    -0.49
    oughlin
    -0.49
     intermédiaire
    -0.48
     før
    -0.47
    HttpDelete
    -0.47
     toilette
    -0.47
    POSITIVE LOGITS
     виправивши
    0.68
    FormTagHelper
    0.66
    CloseOperation
    0.66
     سكانية
    0.62
    \{\\
    0.60
    TestingModule
    0.60
    SOUNDBITE
    0.59
     actionMode
    0.59
    AddTagHelper
    0.58
     <=",
    0.57
    Activations Density 0.868%

    No Known Activations