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. 5987
    Prev
    Next
    INDEX
    Explanations

    direct speech or quotations in the text

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

    Dialogue or quotations

    np_acts-logits-general · gemini-2.0-flash

    saying that, roars way, continued

    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
     Audiodateien
    -0.71
     BorderRadius
    -0.65
    enumi
    -0.61
    CIL
    -0.55
    లాలు
    -0.54
    ****************
    -0.52
     doubtnut
    -0.52
     ')
    
    -0.51
     UIImageView
    -0.50
    jstor
    -0.50
    POSITIVE LOGITS
     I
    0.71
    fjspx
    0.67
    Przypisy
    0.65
     You
    0.65
     invokingState
    0.64
     Brother
    0.64
     Don
    0.63
    SourceChecksum
    0.61
    Brother
    0.61
     Superhost
    0.60
    Activations Density 0.027%

    No Known Activations