© 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. 2-GEMMASCOPE-RES-16K
    11. 3352
    Prev
    Next
    INDEX
    Explanations

    terminology related to linguistic structures and grammatical categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ()(
    -0.52
     препратки
    -0.48
    guenos
    -0.47
    ApiModelProperty
    -0.46
     firm
    -0.45
    ########.
    -0.42
     izle
    -0.41
    гие
    -0.40
    réhen
    -0.39
    ();)
    -0.39
    POSITIVE LOGITS
    ative
    1.53
    ATIVE
    1.31
    atives
    1.16
    rative
    1.03
    ATIVES
    0.89
    atively
    0.89
    atifs
    0.88
    ativen
    0.81
    atif
    0.78
    ctive
    0.77
    Activations Density 2.303%

    No Known Activations