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-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1063
    Prev
    Next
    INDEX
    Explanations

    names and academic affiliations related to mathematicians and their work

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

    Hungarian-related text

    np_acts-logits-general · gemini-2.0-flash

    Hungarian names and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.94
    ьаж
    -0.83
    NameInMap
    -0.81
     avoient
    -0.79
     autorytatywna
    -0.77
    expandindo
    -0.77
    SequentialGroup
    -0.76
     ExecuteAsync
    -0.76
    AddTagHelper
    -0.75
     braccia
    -0.75
    POSITIVE LOGITS
    →
    0.35
     mikro
    0.35
    指
    0.34
    Hozzáférés
    0.34
     stress
    0.34
     „
    0.32
     →
    0.32
     II
    0.32
     ker
    0.31
     vez
    0.31
    Activations Density 0.019%

    No Known Activations