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. 18-GEMMASCOPE-RES-16K
    6. 15544
    Prev
    Next
    INDEX
    Explanations

    terms related to loops and circular structures

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

    relating to circles or loops

    np_acts-logits-general · gemini-2.0-flash

    circle and loop

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.81
    ########.
    -0.64
     sauvage
    -0.56
    XtraEditors
    -0.55
    ications
    -0.55
    menes
    -0.54
    urante
    -0.54
     bỏng
    -0.53
     overras
    -0.53
    asco
    -0.52
    POSITIVE LOGITS
     CIR
    0.87
     loops
    0.86
     circles
    0.82
     loop
    0.82
     circ
    0.80
     CIRC
    0.80
    loop
    0.80
    Loop
    0.77
    LOOP
    0.77
     Loop
    0.76
    Activations Density 0.298%

    No Known Activations