© 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. 7-GEMMASCOPE-RES-16K
    11. 6525
    Prev
    Next
    INDEX
    Explanations

    phrases that describe technical processes and logistical considerations in system configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    extAlignment
    -0.86
    GEBURTSDATUM
    -0.85
    CPtr
    -0.79
     >=",
    -0.74
    IContainer
    -0.73
    jooq
    -0.73
    /*
    -0.72
    AddTagHelper
    -0.70
    TypedDataSet
    -0.69
     nakalista
    -0.69
    POSITIVE LOGITS
    いち
    0.51
     hoeft
    0.46
    TargetException
    0.46
     dags
    0.45
    ctiva
    0.44
     귀
    0.43
     bother
    0.43
     am
    0.43
     costly
    0.43
     unnecessary
    0.42
    Activations Density 0.615%

    No Known Activations