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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 11683
    Prev
    Next
    INDEX
    Explanations

    the concept of distancing or moving away from a topic or situation

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

    "away from" or related semantics

    np_acts-logits-general · gemini-2.0-flash

    away from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     übere
    -0.76
    󠁿
    -0.75
    
    -0.66
    Datuak
    -0.65
     kasarigan
    -0.65
    PageIndex
    -0.65
    UpInside
    -0.63
    FontOfSize
    -0.63
    PositiveButton
    -0.63
    zez
    -0.61
    POSITIVE LOGITS
     from
    0.97
    from
    0.75
    away
    0.71
    Away
    0.66
    NameInMap
    0.65
     away
    0.64
     Away
    0.64
    ArrowToggle
    0.62
    AWAY
    0.60
     FROM
    0.59
    Activations Density 0.265%

    No Known Activations