© 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. 21-GEMMASCOPE-RES-16K
    11. 12838
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases that include the preposition "in" along with contextual elements indicating location or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mangel
    -0.70
    <?
    -0.66
     للمعارف
    -0.62
    Vidite
    -0.61
     Itself
    -0.60
    ographia
    -0.59
    seamnă
    -0.57
     pamamagitan
    -0.56
     cref
    -0.56
    itself
    -0.56
    POSITIVE LOGITS
     charge
    0.92
     possession
    0.77
     touch
    0.74
    charge
    0.69
     receipt
    0.67
     need
    0.67
     trouble
    0.67
     position
    0.66
     danger
    0.64
     custody
    0.64
    Activations Density 0.237%

    No Known Activations