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. 8096
    Prev
    Next
    INDEX
    Explanations

    code snippets that define and utilize functions or methods, particularly in object-oriented programming contexts

    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
    AddTagHelper
    -0.61
     kaarangay
    -0.51
    بوابة
    -0.50
     cultures
    -0.49
    şekkür
    -0.48
    motic
    -0.48
     gyhoeddwyd
    -0.47
    iane
    -0.46
    éenne
    -0.46
     Yoshida
    -0.46
    POSITIVE LOGITS
     methods
    1.33
     method
    1.30
     Methods
    1.25
    methods
    1.24
    method
    1.20
     Method
    1.18
    Methods
    1.15
    Method
    1.13
     METHODS
    1.10
     METHOD
    1.06
    Activations Density 0.878%

    No Known Activations