© 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. 22-GEMMASCOPE-RES-16K
    11. 14224
    Prev
    Next
    INDEX
    Explanations

    narratives or stories conveyed through various mediums

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

    preceding or related to "story"

    np_acts-logits-general · gemini-2.0-flash

    telling story

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Configurer
    -0.53
    DispatchToProps
    -0.52
    Nuorodos
    -0.52
     disponibilités
    -0.49
     hObject
    -0.48
    eseorang
    -0.48
    fieldId
    -0.48
    DockStyle
    -0.47
    Населення
    -0.47
    SCHEDULE
    -0.46
    POSITIVE LOGITS
     story
    3.09
     stories
    2.77
    story
    2.58
    Story
    2.47
     Story
    2.46
     STORY
    2.40
    stories
    2.35
    Stories
    2.27
     tale
    2.26
     Stories
    2.21
    Activations Density 0.320%

    No Known Activations