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. 22-GEMMASCOPE-RES-16K
    6. 12868
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to software licensing

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

    Kubernetes and client-gen code

    np_acts-logits-general · gemini-2.0-flash

    pod and colors definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     onPostExecute
    -0.63
     forgets
    -0.62
    DoubleQuotes
    -0.60
     forgetting
    -0.57
    Xna
    -0.56
    oubliez
    -0.54
     Merrill
    -0.53
     forgot
    -0.52
     forgotten
    -0.52
    دانشنامهٔ
    -0.51
    POSITIVE LOGITS
    bootstrapcdn
    0.68
     Pod
    0.68
     kub
    0.63
     pod
    0.61
    Personensuche
    0.61
     CreateTagHelper
    0.61
    Pod
    0.59
     Kubernetes
    0.56
     POD
    0.56
     pods
    0.55
    Activations Density 0.199%

    No Known Activations