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. 14-GEMMASCOPE-RES-16K
    6. 8337
    Prev
    Next
    INDEX
    Explanations

    references to different phases or stages in a process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     electricidad
    -0.65
    Rüyada
    -0.58
    <bos>
    -0.56
     fumée
    -0.56
     negru
    -0.55
    électricité
    -0.53
     gouvern
    -0.52
     financieras
    -0.52
     hospitales
    -0.52
     metálico
    -0.52
    POSITIVE LOGITS
     phase
    1.45
     stage
    1.40
     Phase
    1.38
    phase
    1.33
     Stage
    1.32
    Phase
    1.32
    Stage
    1.24
     PHASE
    1.23
     stages
    1.20
     STAGE
    1.20
    Activations Density 0.063%

    No Known Activations