© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 2982
    Prev
    Next
    INDEX
    Explanations

    method definitions and their parameters in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChildScrollView
    -0.50
     SafeMath
    -0.50
    iomanip
    -0.49
    ัติ
    -0.48
    opsida
    -0.47
    ⓘ
    -0.46
     برانيه
    -0.45
     springfox
    -0.45
     resultCode
    -0.45
    msgSender
    -0.45
    POSITIVE LOGITS
    CodeAttribute
    0.66
    bibitem
    0.61
    DebuggerNonUser
    0.61
    shimano
    0.59
    AccessorTable
    0.58
    ngOnInit
    0.57
    TagMode
    0.56
    олові
    0.55
    InstanceState
    0.54
    otheek
    0.54
    Activations Density 0.117%

    No Known Activations