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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 6232
    Prev
    Next
    INDEX
    Explanations

    references to television networks and their programming

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

    Television channels or networks

    np_acts-logits-general · gemini-2.0-flash

    TV channels and networks

    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
     EconPapers
    -0.55
     portero
    -0.49
    contrar
    -0.48
     Conſ
    -0.48
     елның
    -0.47
    dafx
    -0.46
     invokingState
    -0.45
    SharedCtor
    -0.45
    GDPR
    -0.44
    rollment
    -0.44
    POSITIVE LOGITS
     channel
    0.63
    odeon
    0.62
     MTV
    0.62
    zeera
    0.60
     channels
    0.59
    MTV
    0.59
     TV
    0.57
     Channel
    0.56
     ESPN
    0.54
     tv
    0.48
    Activations Density 0.202%

    No Known Activations