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. 18-GEMMASCOPE-RES-16K
    6. 1928
    Prev
    Next
    INDEX
    Explanations

    concepts related to overcoming past struggles and personal transformation

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

    the past

    np_acts-logits-general · gemini-2.0-flash

    past and its related concepts

    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
     MonoBehaviour
    -0.57
    正規
    -0.54
    UserScript
    -0.52
    WireFormatLite
    -0.52
    zetten
    -0.51
    ⓧ
    -0.51
     Mostra
    -0.49
    cetti
    -0.49
    pture
    -0.49
    ducción
    -0.48
    POSITIVE LOGITS
     past
    2.41
    past
    1.98
     Past
    1.98
    Past
    1.90
     Vergangenheit
    1.78
     PAST
    1.75
     history
    1.66
    PAST
    1.57
     passato
    1.57
     pasado
    1.56
    Activations Density 0.221%

    No Known Activations