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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6374
    Prev
    Next
    INDEX
    Explanations

    phrases and contexts indicating representation or advocacy for someone or a group

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

    "On behalf of"

    np_acts-logits-general · gemini-2.0-flash

    on behalf of

    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
    阅
    -0.39
    ʑ
    -0.34
     risult
    -0.34
     konk
    -0.34
    ปร
    -0.33
     préciser
    -0.33
     apparaître
    -0.33
     passieren
    -0.33
     Riyadh
    -0.33
     كومونز
    -0.33
    POSITIVE LOGITS
     behalf
    1.69
     باسم
    0.73
     AssemblyCompany
    0.72
     mewakili
    0.72
    representing
    0.67
    yntaxException
    0.63
     forState
    0.61
    ArgumentParser
    0.60
     Representing
    0.59
     representing
    0.59
    Activations Density 0.232%

    No Known Activations