© 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. 12-GEMMASCOPE-RES-16K
    11. 14540
    Prev
    Next
    INDEX
    Explanations

    phrases and clauses containing various forms of punctuation and conjunctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     adipis
    -0.62
    SerializedName
    -0.59
    +#+#
    -0.54
    HideFlags
    -0.52
    GraphicsUnit
    -0.52
    brido
    -0.51
    ########.
    -0.51
    AxisAlignment
    -0.50
     насељу
    -0.48
    Leve
    -0.48
    POSITIVE LOGITS
     referenties
    0.72
     betweenstory
    0.60
     etc
    0.56
     Италијани
    0.55
    expandindo
    0.55
     Etc
    0.53
    TagHelper
    0.52
    xFFFFFFFF
    0.50
    yarnpkg
    0.49
     متعلقه
    0.49
    Activations Density 0.434%

    No Known Activations