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. 4398
    Prev
    Next
    INDEX
    Explanations

    code import statements in Java

    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
    GenerationType
    -0.54
     MEAN
    -0.49
     ...
    
    -0.46
     wetting
    -0.46
     Meaning
    -0.44
     Mean
    -0.44
    ządu
    -0.43
    ...\
    -0.43
    discord
    -0.42
    SerializedName
    -0.42
    POSITIVE LOGITS
     java
    0.75
     javax
    0.75
    enumi
    0.69
    oa̍t
    0.65
    LookAnd
    0.65
    ISupport
    0.64
     متعلقه
    0.64
    WriteTagHelper
    0.60
    hasMoreElements
    0.60
     مشين
    0.60
    Activations Density 0.087%

    No Known Activations