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. 2-GEMMASCOPE-RES-16K
    6. 6655
    Prev
    Next
    INDEX
    Explanations

    references to direction or positioning to the right

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    matchCondition
    -0.86
    oredCriteria
    -0.83
    Autoritní
    -0.81
    peicher
    -0.74
     Cascades
    -0.72
    CMYK
    -0.71
     ProtoMessage
    -0.71
     Scherer
    -0.69
    Abitanti
    -0.69
    期刊论文
    -0.69
    POSITIVE LOGITS
    right
    3.09
     right
    3.00
     Right
    2.91
    Right
    2.91
    RIGHT
    2.70
     RIGHT
    2.63
    setRight
    2.04
     righ
    1.97
    getRight
    1.96
    右
    1.74
    Activations Density 0.120%

    No Known Activations