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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 2137
    Prev
    Next
    INDEX
    Explanations

    legal and regulatory terms related to restrictions and sanctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    legislative actions and their implications

    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
    onViewCreated
    -0.61
    abestanden
    -0.58
    webElement
    -0.58
    kloped
    -0.54
    мені
    -0.51
    esez
    -0.49
    SOUNDBITE
    -0.49
    WEBPACK
    -0.48
    ordeel
    -0.47
     pulumi
    -0.47
    POSITIVE LOGITS
     restrictions
    0.87
     rules
    0.85
     controls
    0.84
     limits
    0.82
     regulations
    0.82
     caps
    0.74
     requirements
    0.74
     curbs
    0.71
     limitations
    0.71
     strict
    0.69
    Activations Density 0.554%

    No Known Activations