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. 4000
    Prev
    Next
    INDEX
    Explanations

    titles of films

    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
    jestel
    -0.61
     NSCoder
    -0.60
    原始内容存档于
    -0.59
    ="@+
    -0.55
     Design
    -0.49
    assum
    -0.49
     跳转至
    -0.49
    ContentAsync
    -0.49
    Autoritní
    -0.48
    imageshack
    -0.48
    POSITIVE LOGITS
     written
    1.12
     directed
    1.10
     starring
    1.09
     adapted
    0.98
    written
    0.92
     based
    0.91
    directed
    0.88
     produced
    0.87
     released
    0.85
    adapted
    0.84
    Activations Density 0.332%

    No Known Activations