© 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. 7160
    Prev
    Next
    INDEX
    Explanations

    contractions and positive affirmations in the text

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

    Contractions ending in "'s" or "'ve"

    np_acts-logits-general · gemini-2.0-flash

    it's followed by various words

    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
    queryInterface
    -0.90
    WriteTagHelper
    -0.85
    曖昧さ回避
    -0.77
    protoimpl
    -0.77
     createSlice
    -0.76
     esternos
    -0.76
     utafitiHapana
    -0.72
    MarshalTo
    -0.72
    MemoryWarning
    -0.67
    enfone
    -0.67
    POSITIVE LOGITS
     funny
    0.68
     amazing
    0.67
     such
    0.62
     always
    0.62
     ironic
    0.61
     not
    0.60
     unfortunate
    0.59
     just
    0.58
     strange
    0.57
     zwar
    0.56
    Activations Density 0.121%

    No Known Activations