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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6521
    Prev
    Next
    INDEX
    Explanations

    keywords and terms associated with finite state machines and state transitions in programming

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

    Code, states, or transitions

    np_acts-logits-general · gemini-2.0-flash

    states and transitions

    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
     Peasant
    -0.51
     оригіналу
    -0.50
    EndContext
    -0.50
    BindingResult
    -0.49
    MessageTagHelper
    -0.48
    ioutil
    -0.48
    caneca
    -0.47
    RegressionTest
    -0.47
    droje
    -0.46
    RegistryLite
    -0.45
    POSITIVE LOGITS
    stateProvider
    0.59
    StateMachine
    0.49
     states
    0.46
    states
    0.46
    States
    0.45
     States
    0.43
     transition
    0.41
     STATES
    0.40
    nextState
    0.40
     transitions
    0.39
    Activations Density 0.921%

    No Known Activations