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 - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 90776
    Prev
    Next
    INDEX
    Explanations

    terms related to licensing and failure handling in programming

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

    goto out;

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    <eos>
    -0.46
    ↵↵
    -0.43
    if
    -0.41
    ↵
    -0.37
    make
    -0.36
    '''
    -0.35
    /*
    -0.35
    create
    -0.34
    1
    -0.33
    tr
    -0.33
    POSITIVE LOGITS
    httphttps
    1.45
    脚注の使い方
    1.06
    CppMethod
    0.97
     renamed
    0.95
    __(/*!
    0.93
    interopRequire
    0.93
    Personendaten
    0.93
    AddTagHelper
    0.93
     Chwiliwch
    0.93
    دانشنامهٔ
    0.92
    Activations Density 0.003%

    No Known Activations