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. 15-GEMMASCOPE-RES-16K
    6. 1948
    Prev
    Next
    INDEX
    Explanations

    scientific processes and methodologies, especially in research experiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 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
    principalTable
    -0.46
    rizona
    -0.46
    setVerticalGroup
    -0.44
    nhung
    -0.44
     OFDb
    -0.42
    madison
    -0.42
    hésite
    -0.42
    هرست
    -0.39
    RTEE
    -0.39
     चीज़ों
    -0.39
    POSITIVE LOGITS
     createSprite
    0.50
    UrlResolution
    0.40
     متحده
    0.39
     further
    0.39
     subsequently
    0.38
     defaultstate
    0.38
    SourceChecksum
    0.38
     صوتيه
    0.36
    CreateModel
    0.35
    今度は
    0.34
    Activations Density 2.088%

    No Known Activations