© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10990
    Prev
    Next
    INDEX
    Explanations

    specific sequences and their analyses in a scientific context

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

    "sequence" and its related forms

    np_acts-logits-general · gemini-2.0-flash

    sequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mittedly
    -0.35
     escritório
    -0.33
    mrb
    -0.32
     ioutil
    -0.31
     כן
    -0.31
     Talking
    -0.31
     оригіналу
    -0.31
    WebVitals
    -0.29
     kişilik
    -0.29
     udrž
    -0.29
    POSITIVE LOGITS
     sequence
    2.36
     Sequence
    2.27
    sequence
    2.20
    Sequence
    2.19
     sequences
    2.13
     Sequences
    2.02
     SEQUENCE
    1.99
    SEQUENCE
    1.88
    Sequences
    1.88
     seq
    1.84
    Activations Density 0.207%

    No Known Activations