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. 83086
    Prev
    Next
    INDEX
    Explanations

    the verb "is" and its usage in various contexts

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

    is followed by noun phrase

    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
     lâmpada
    -0.41
     criança
    -0.40
     armée
    -0.40
     Abends
    -0.38
     navy
    -0.37
     cadeira
    -0.36
     pengaruh
    -0.36
     influência
    -0.35
     álcool
    -0.34
     estrela
    -0.33
    POSITIVE LOGITS
    WebElementEntity
    0.64
    IBOutlet
    0.59
    MemoryWarning
    0.57
    ftagPool
    0.53
     autorytatywna
    0.51
     referrerpolicy
    0.50
    StoryboardSegue
    0.50
    transQ
    0.50
    GIVEREF
    0.50
    matchCondition
    0.49
    Activations Density 0.009%

    No Known Activations