Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 9466
    Prev
    Next
    INDEX
    Explanations

    words related to migration and movement patterns

    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
     Fairbanks
    -0.69
    epres
    -0.66
    cephala
    -0.66
    gebob
    -0.64
     good
    -0.63
    Pres
    -0.62
     Good
    -0.61
    Good
    -0.60
    handlebars
    -0.58
     Colts
    -0.58
    POSITIVE LOGITS
     migration
    1.53
     migrated
    1.45
    Migrate
    1.40
     Migration
    1.38
     migrating
    1.38
     Migrate
    1.36
     migrations
    1.35
     migrate
    1.34
     mig
    1.31
     migrants
    1.31
    Activations Density 0.183%

    No Known Activations