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. 25-GEMMASCOPE-RES-16K
    6. 1799
    Prev
    Next
    INDEX
    Explanations

    uniform resource identifier (URI) components related to tracking or analytics parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tartalomajánló
    -0.53
     Bahadur
    -0.49
    goed
    -0.49
    regado
    -0.47
    thansa
    -0.47
     препратки
    -0.47
    hyp
    -0.45
    AsUp
    -0.45
    angles
    -0.45
     Elements
    -0.45
    POSITIVE LOGITS
    source
    1.49
     source
    1.13
    SOURCE
    0.92
     SOURCE
    0.91
     Source
    0.88
    Source
    0.87
    sourced
    0.72
    sou
    0.72
    Personendaten
    0.70
    ource
    0.70
    Activations Density 0.189%

    No Known Activations