© 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. 24-GEMMASCOPE-RES-16K
    11. 8004
    Prev
    Next
    INDEX
    Explanations

    references to personal memories and emotional experiences

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

    lasting impact or memory

    np_acts-logits-general · gemini-2.0-flash

    things that stay with you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.77
     dipu
    -0.57
     mapStateToProps
    -0.54
    antMatchers
    -0.54
     avanza
    -0.53
     auffi
    -0.53
    :+:
    -0.52
    KommentareTeilen
    -0.52
    mybatisplus
    -0.51
     dispensing
    -0.51
    POSITIVE LOGITS
     haunts
    0.91
     haunt
    0.87
     haunting
    0.87
     lodged
    0.79
     haunted
    0.77
     stuck
    0.75
     gna
    0.73
     etched
    0.72
     reverber
    0.72
     imprinted
    0.72
    Activations Density 0.288%

    No Known Activations