© 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. 19-GEMMASCOPE-RES-16K
    11. 2780
    Prev
    Next
    INDEX
    Explanations

    emotional and relational expressions regarding attachment and feedback about interpersonal interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    تقاوى
    -0.67
     المعيارى
    -0.64
    postsleuth
    -0.61
    UserScript
    -0.58
    帖最后由
    -0.58
    FTFY
    -0.57
    Historia
    -0.56
     utafitiHapana
    -0.53
    /*++
    -0.52
     Reverso
    -0.51
    POSITIVE LOGITS
    }]);
    0.61
     ruled
    0.58
     AssemblyTitle
    0.57
    URUS
    0.57
    InjectMocks
    0.55
     كومونز
    0.54
    ionage
    0.54
     Saturn
    0.53
    ()]);
    0.53
    uran
    0.53
    Activations Density 0.041%

    No Known Activations