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. 21-GEMMASCOPE-RES-16K
    6. 12496
    Prev
    Next
    INDEX
    Explanations

    sentences describing interactions and the transfer of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OrNil
    -0.65
    الدراسه
    -0.56
    })));
    -0.49
    testcase
    -0.47
    rawtypes
    -0.44
    resas
    -0.43
    timewa
    -0.43
     Valhalla
    -0.43
     recherchez
    -0.43
     aceptas
    -0.42
    POSITIVE LOGITS
     communication
    2.29
     communicate
    2.01
     communicating
    1.99
     Communication
    1.96
    Communication
    1.93
    communication
    1.89
     communications
    1.84
     COMMUNICATION
    1.83
     communicates
    1.80
     communicative
    1.74
    Activations Density 0.441%

    No Known Activations