© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 1370
    Prev
    Next
    INDEX
    Explanations

    phrases related to social dynamics and group behaviors, particularly where individuals are considered in terms of their influence and acceptance within a community

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CppMethod
    -0.68
    MENAFN
    -0.63
     PyObject
    -0.59
    DockStyle
    -0.56
    XmlAccessType
    -0.55
    Hauptartikel
    -0.52
    )(((
    -0.52
    shafen
    -0.51
    ApiOperation
    -0.50
    WriteBarrier
    -0.49
    POSITIVE LOGITS
     Pourtant
    0.78
     Wrong
    0.73
     wrong
    0.72
     WRONG
    0.71
     falschen
    0.67
    Wrong
    0.66
    WRONG
    0.65
    殊
    0.65
     forgetting
    0.63
     falsche
    0.63
    Activations Density 0.508%

    No Known Activations