© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 522
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of "drop."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "drop" and its variations like "dropped," "dropdown," and "droppable."

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ftagPool
    -0.59
    SequentialGroup
    -0.59
     endblock
    -0.52
    posedge
    -0.51
    TintMode
    -0.47
    VIAF
    -0.46
    TemporalType
    -0.45
    MergeFrom
    -0.45
    UserScript
    -0.44
    newBuilder
    -0.44
    POSITIVE LOGITS
     drop
    1.57
     Drop
    1.53
    Drop
    1.44
    drop
    1.43
     DROP
    1.41
     dropped
    1.39
     dropping
    1.30
     drops
    1.27
    DROP
    1.27
     Dro
    1.23
    Activations Density 0.065%

    No Known Activations