© 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. 25-GEMMASCOPE-RES-16K
    11. 8198
    Prev
    Next
    INDEX
    Explanations

    elements related to spatial descriptions and features within various environments or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.61
    everywhere
    -0.59
    tserrat
    -0.56
    ########.
    -0.54
    ísimas
    -0.53
     démocratique
    -0.52
     egiten
    -0.52
     snippetHide
    -0.52
    OrNil
    -0.52
    #+#
    -0.51
    POSITIVE LOGITS
     area
    1.14
    area
    0.94
     AREA
    0.85
     Area
    0.84
     área
    0.83
    Area
    0.83
     complete
    0.72
    área
    0.70
    AREA
    0.68
     leading
    0.67
    Activations Density 0.210%

    No Known Activations