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. 12-GEMMASCOPE-RES-16K
    6. 7363
    Prev
    Next
    INDEX
    Explanations

    references to specific objects or items, particularly those linked to clips and clips associated with physical objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.97
    StoryboardSegue
    -0.81
     ujednoznacz
    -0.81
     doInBackground
    -0.78
     AssemblyVersion
    -0.76
    Demografía
    -0.74
    DataMember
    -0.74
     McE
    -0.73
     Rasmussen
    -0.72
     bianca
    -0.72
    POSITIVE LOGITS
     clips
    0.89
     Kew
    0.80
     dongle
    0.80
     Clips
    0.79
     Gij
    0.78
     Clip
    0.78
    clips
    0.77
    сунок
    0.74
     GOT
    0.74
     Rik
    0.73
    Activations Density 0.635%

    No Known Activations