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. 2-GEMMASCOPE-RES-16K
    6. 15236
    Prev
    Next
    INDEX
    Explanations

    code-related conditional statements and error handling constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CodedInputStream
    -0.69
    rovnik
    -0.67
    ContentLoaded
    -0.63
     esternos
    -0.60
    MethodManager
    -0.59
     lenker
    -0.58
    uramente
    -0.57
     OFDb
    -0.57
     ISNI
    -0.56
     getRule
    -0.55
    POSITIVE LOGITS
    Personendaten
    0.59
     kurz
    0.47
    ższych
    0.47
     муніципалі
    0.46
    izowane
    0.46
    MetaObject
    0.45
    feinander
    0.45
     nemlig
    0.42
    uurs
    0.42
    atamente
    0.42
    Activations Density 0.308%

    No Known Activations