© 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. 9753
    Prev
    Next
    INDEX
    Explanations

    expressions of personal statements and queries

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

    conversational phrases that introduce hypothetical scenarios or examples, particularly "Let's say" and "Say I".

    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
     متعلقه
    -0.50
    исленность
    -0.50
    ///</
    -0.47
    
    -0.45
     tiende
    -0.44
    ArrowToggle
    -0.41
    цезда
    -0.40
    feeling
    -0.39
    Abit
    -0.39
     removeFrom
    -0.39
    POSITIVE LOGITS
     have
    1.39
     memiliki
    1.35
     mempunyai
    1.28
     possess
    1.26
     having
    1.22
     possesses
    1.22
     иметь
    1.18
     posiad
    1.18
     punya
    1.15
     Memiliki
    1.09
    Activations Density 1.058%

    No Known Activations