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. 2664
    Prev
    Next
    INDEX
    Explanations

    terms related to directional movement or progression toward an objective

    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
     Calvo
    -0.81
     foglal
    -0.71
     riuscito
    -0.70
    nsf
    -0.67
    5
    -0.65
    물
    -0.65
    T
    -0.64
     poffe
    -0.63
    ház
    -0.61
     Shetland
    -0.60
    POSITIVE LOGITS
    toward
    1.79
     Toward
    1.72
     toward
    1.70
    towards
    1.67
     Towards
    1.66
    Towards
    1.63
    Toward
    1.62
     towards
    1.53
     envers
    1.15
     hacia
    1.15
    Activations Density 0.065%

    No Known Activations