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. 118950
    Prev
    Next
    INDEX
    Explanations

    symbols and characters used in programming or coding contexts

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

    assignment and list delimiters

    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
    mobileqq
    -0.43
     intptr
    -0.40
     aldea
    -0.39
     NUKAT
    -0.39
    BufferException
    -0.39
    文件中
    -0.38
    jecture
    -0.38
    sweise
    -0.37
    KURZBESCHREIBUNG
    -0.37
     campaña
    -0.37
    POSITIVE LOGITS
    =”
    2.48
    =’
    1.38
    =“
    1.04
    (“
    0.88
    :”
    0.81
    =\"
    0.75
    (‘
    0.72
     “…
    0.71
    …”
    0.71
     …”
    0.69
    Activations Density 0.008%

    No Known Activations