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. 8029
    Prev
    Next
    INDEX
    Explanations

    references to political events and statements

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

    Immediately before a non-alphabetic character

    np_acts-logits-general · gemini-2.0-flash

    specific days of the week

    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
     uș
    -0.66
     behaviors
    -0.66
     Behaviors
    -0.60
     își
    -0.59
    seamnă
    -0.58
     picioare
    -0.57
     edelstahl
    -0.55
     puteți
    -0.53
     idag
    -0.53
    చు
    -0.52
    POSITIVE LOGITS
    WriteBarrier
    0.81
    DebuggerNonUser
    0.76
     lakh
    0.69
     unauthorised
    0.68
     afresh
    0.67
     Sebab
    0.67
     مشين
    0.66
    ]-->
    0.65
    ,’’
    0.65
    __":
    0.64
    Activations Density 0.193%

    No Known Activations