© 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. 24-GEMMASCOPE-RES-16K
    6. 2103
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structures, particularly related to loops and conditional statements

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

    Iterating through lists or sets

    np_acts-logits-general · gemini-2.0-flash

    for loop iteration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <=",
    -0.63
    EDEFAULT
    -0.63
     '/';
    -0.62
     resourceCulture
    -0.62
    contentLoaded
    -0.62
    httphttps
    -0.61
    TestingModule
    -0.60
     '\\;'
    -0.59
    __*/
    -0.59
     "/";
    -0.58
    POSITIVE LOGITS
     item
    1.18
     each
    1.07
    item
    0.98
    each
    0.97
     element
    0.96
     entry
    0.86
     elem
    0.85
    EACH
    0.85
    Each
    0.85
     Each
    0.83
    Activations Density 0.188%

    No Known Activations