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. 18-GEMMASCOPE-RES-16K
    6. 5117
    Prev
    Next
    INDEX
    Explanations

    lines of code related to image and file handling functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets involving files or system calls

    np_acts-logits-general · gemini-2.0-flash

    code and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnknownFields
    -0.68
     disambiguazione
    -0.63
    Personensuche
    -0.63
    NewGuid
    -0.55
    WriteBarrier
    -0.54
    HtmlAttribute
    -0.54
    complexType
    -0.53
     minOccurs
    -0.52
    LookAnd
    -0.51
    IUrlHelper
    -0.51
    POSITIVE LOGITS
    IContainer
    0.66
     للمعارف
    0.66
    Underlying
    0.63
    لينكات
    0.60
     Underlying
    0.59
    ">:
    0.59
    AnimationsModule
    0.57
     igång
    0.57
    ">'.$
    0.57
    chle
    0.56
    Activations Density 0.615%

    No Known Activations