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. 15-GEMMASCOPE-RES-16K
    6. 4101
    Prev
    Next
    INDEX
    Explanations

    instances of the word "input" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Berikut
    -0.76
     exacte
    -0.76
    zeppelin
    -0.75
     exclusivas
    -0.73
     morire
    -0.73
     Wale
    -0.73
     handelt
    -0.72
     posteriore
    -0.72
     cohomology
    -0.72
    География
    -0.72
    POSITIVE LOGITS
     INPUT
    1.38
     input
    1.34
     Input
    1.31
     inputs
    1.28
    setInput
    1.26
    INPUT
    1.26
     Inputs
    1.22
    Input
    1.18
     输入
    1.10
    Inputs
    1.07
    Activations Density 0.082%

    No Known Activations