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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 7248
    Prev
    Next
    INDEX
    Explanations

    indicators of change or transition within a narrative context

    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
     v
    -0.47
     grond
    -0.46
     people
    -0.42
    ((
    -0.41
     x
    -0.40
    gb
    -0.39
     Hub
    -0.38
     est
    -0.38
     *
    -0.38
    times
    -0.38
    POSITIVE LOGITS
    tagHelperRunner
    1.35
    Portail
    1.32
     disambiguazione
    1.28
    oredCriteria
    1.21
    MigrationBuilder
    1.16
    verwijspagina
    1.15
    Personensuche
    1.13
    DeleteBehavior
    1.10
     ujednoznacz
    1.10
     itſelf
    1.08
    Activations Density 0.217%

    No Known Activations