© 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. 16089
    Prev
    Next
    INDEX
    Explanations

    elements related to programming structures and data types

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

    array or string indexing operations with subtraction from length or size.

    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
    AndEndTag
    -0.44
     Next
    -0.38
     Later
    -0.37
     amb
    -0.35
     Box
    -0.34
     Mis
    -0.34
    Next
    -0.34
    berus
    -0.33
    loom
    -0.33
    Later
    -0.33
    POSITIVE LOGITS
     disambiguazione
    0.57
     LEYENDO
    0.55
    ()-
    0.53
    seamnă
    0.53
     <<<<<<<<<<<<<<
    0.52
     gyhoeddwyd
    0.51
     Numerade
    0.50
    actéristi
    0.50
    ágenes
    0.50
    Gambas
    0.50
    Activations Density 0.529%

    No Known Activations