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-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 1000
    Prev
    Next
    INDEX
    Explanations

    phrases related to project planning and development processes

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

    "implement" or "design"

    np_acts-logits-general · gemini-2.0-flash

    implementing and executing plans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verwijspagina
    -0.67
    NOPQRST
    -0.66
    aarrggbb
    -0.66
     distanciation
    -0.57
    orsese
    -0.56
    ariConfig
    -0.55
    EDEFAULT
    -0.53
    UnitTesting
    -0.52
    SharedCtor
    -0.50
     prieten
    -0.50
    POSITIVE LOGITS
     implementation
    1.74
     execution
    1.73
     Implementation
    1.56
     Execution
    1.53
    implementation
    1.52
     execute
    1.47
    Implementation
    1.46
     implemented
    1.45
     implement
    1.43
     executed
    1.43
    Activations Density 0.603%

    No Known Activations