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. 4587
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and constructs related to optional elements and imports

    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
     espirituales
    -0.31
    tahankan
    -0.31
    aucun
    -0.30
     noires
    -0.28
     particulières
    -0.28
     violenza
    -0.28
    「
    -0.28
    南
    -0.28
    夏
    -0.28
    anskje
    -0.28
    POSITIVE LOGITS
    Params
    0.42
    Config
    0.41
    Instance
    0.40
    Attribute
    0.39
    Entity
    0.39
    Filter
    0.38
    Value
    0.38
    MetaData
    0.38
    Parameters
    0.38
    Resource
    0.38
    Activations Density 22.397%

    No Known Activations