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. 17-GEMMASCOPE-RES-16K
    6. 7005
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "string" in various contexts, indicating a focus on string data types or operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.83
    ngdoc
    -0.68
     Obrador
    -0.68
    сылкі
    -0.66
     kool
    -0.65
    πως
    -0.63
     Morpho
    -0.63
     lande
    -0.62
     rendus
    -0.61
     paroisse
    -0.61
    POSITIVE LOGITS
     strings
    1.15
     string
    1.07
    strings
    1.03
     Strings
    1.00
    STRING
    0.99
     STRING
    0.96
     Stringer
    0.94
    Strings
    0.90
    setString
    0.88
    string
    0.85
    Activations Density 0.105%

    No Known Activations