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. 25-GEMMASCOPE-RES-16K
    6. 3578
    Prev
    Next
    INDEX
    Explanations

    technical terms and measurements typically used in scientific or specialized contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CMM
    -0.62
     CJ
    -0.61
     CSM
    -0.60
     CS
    -0.57
     CE
    -0.54
     CW
    -0.54
     CP
    -0.54
    CSM
    -0.54
     CSD
    -0.53
     CF
    -0.52
    POSITIVE LOGITS
     PEC
    1.08
     WAC
    1.07
     MCC
    1.04
     RIC
    1.03
     TAC
    1.03
     SDC
    1.03
     Hickey
    1.03
     HEC
    1.02
     PCC
    1.02
    Hic
    1.01
    Activations Density 4.381%

    No Known Activations