© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 5423
    Prev
    Next
    INDEX
    Explanations

    expressions indicating direction or progression towards an outcome

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Toward" or "towards"

    np_acts-logits-general · gemini-2.0-flash

    direction towards something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     foglal
    -0.73
     rimasto
    -0.70
     Calvo
    -0.69
     assoluto
    -0.68
     riuscito
    -0.67
    setopt
    -0.66
    badi
    -0.65
    morphic
    -0.65
     Integrity
    -0.65
     kapcs
    -0.64
    POSITIVE LOGITS
     toward
    1.65
    toward
    1.60
    towards
    1.50
     towards
    1.48
    Toward
    1.42
     Toward
    1.42
     Towards
    1.37
    Towards
    1.36
     TOW
    0.98
     hacia
    0.95
    Activations Density 0.086%

    No Known Activations