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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 25-GEMMASCOPE-RES-16K
    6. 3002
    Prev
    Next
    INDEX
    Explanations

    terms related to web development and query management

    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
     CreateTagHelper
    -0.59
     vibes
    -0.55
     Roskov
    -0.55
     vibe
    -0.55
     BoxDecoration
    -0.54
    orld
    -0.54
     الحره
    -0.54
     disambiguazione
    -0.53
     world
    -0.52
    INDUSTRY
    -0.51
    POSITIVE LOGITS
    osoba
    0.53
     agreed
    0.51
     Documents
    0.51
     указа
    0.51
    Documents
    0.50
     сведения
    0.49
     CURLOPT
    0.49
     préciser
    0.49
     cheval
    0.48
     заявление
    0.48
    Activations Density 0.010%

    No Known Activations