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. 3991
    Prev
    Next
    INDEX
    Explanations

    functions and methods specifically related to managing user data within a programming context

    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
     snippetHide
    -0.62
    adpleegd
    -0.62
    AddTagHelper
    -0.61
     Edizioni
    -0.50
    detectChanges
    -0.50
    XtraGrid
    -0.49
    IVEREF
    -0.48
    Література
    -0.45
     getPrice
    -0.44
     gambling
    -0.43
    POSITIVE LOGITS
     Person
    1.47
    Person
    1.41
     person
    1.38
     PERSON
    1.35
    PERSON
    1.34
    person
    1.32
     profiles
    1.25
     persons
    1.24
     Profile
    1.22
     profile
    1.21
    Activations Density 0.566%

    No Known Activations