© 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. 25-GEMMASCOPE-RES-16K
    6. 8274
    Prev
    Next
    INDEX
    Explanations

    references to birds and their interactions with the environment

    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
     Lyons
    -0.68
     werewolf
    -0.60
     Zahn
    -0.57
     Mier
    -0.55
     dental
    -0.55
     دندان
    -0.54
     dente
    -0.54
    ropathy
    -0.54
     Deane
    -0.53
     pork
    -0.53
    POSITIVE LOGITS
     bird
    1.96
     birds
    1.86
     Bird
    1.82
     Birds
    1.73
    Bird
    1.71
     avian
    1.69
     feathers
    1.65
     BIRD
    1.63
    Birds
    1.59
    bird
    1.59
    Activations Density 0.555%

    No Known Activations