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. 23-GEMMASCOPE-RES-16K
    6. 12516
    Prev
    Next
    INDEX
    Explanations

    terms related to actions, processes, and improvements associated with real estate transactions and personal management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PyExc
    -0.69
     يتيمه
    -0.59
     Conversely
    -0.58
    Conversely
    -0.57
     devrez
    -0.54
     dirilis
    -0.53
    enterOuterAlt
    -0.52
    LogFactory
    -0.51
    RepeatedField
    -0.49
     cérami
    -0.49
    POSITIVE LOGITS
     maximum
    0.77
     evidences
    0.76
     utmost
    0.75
     الاطلاع
    0.73
     proper
    0.73
     lot
    0.72
     huge
    0.70
     immense
    0.69
     lots
    0.69
     sufficient
    0.68
    Activations Density 0.322%

    No Known Activations